© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13204
    Prev
    Next
    INDEX
    Explanations

    kilometres per week

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron chiefly activates on numeric and measurement tokens, picking out prices, mileage figures, model years, and other specification numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    product listings and descriptions, especially for vehicles and mechanical items with detailed specifications.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of vehicles in listings or reviews, especially dealer-style specs, mileage, trims, features, and service/ownership details.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sprzę
    0.56
     proportions
    0.55
     سلط
    0.55
     Größen
    0.54
     horsepower
    0.54
     හො
    0.54
     السيارات
    0.52
    คง
    0.51
    bhp
    0.51
     Иванов
    0.51
    POSITIVE LOGITS
     mileage
    0.75
     racked
    0.74
    miles
    0.68
     Mileage
    0.68
    公里
    0.67
     CpG
    0.66
    kms
    0.66
     clocked
    0.66
     KM
    0.66
    Mileage
    0.66
    Activations Density 0.121%

    No Known Activations