© 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. 2578
    Prev
    Next
    INDEX
    Explanations

    vintage, classic, or antique items

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

    The neuron primarily detects numerical tokens (digits and multi-digit numbers) in the text.

    oai_token-act-pair · o4-miniTriggered 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
     infotainment
    0.76
    🛴
    0.75
     kendaraan
    0.74
     automó
    0.73
     assistenza
    0.73
     автомобиль
    0.72
    🅿
    0.71
     vehículos
    0.71
     автомобиля
    0.71
    🚗
    0.71
    POSITIVE LOGITS
     vintage
    1.21
     Vintage
    1.15
    vintage
    1.06
    Vintage
    1.05
     Classic
    0.98
     classic
    0.92
     antique
    0.89
     Antique
    0.82
    仿
    0.79
    Classic
    0.78
    Activations Density 0.551%

    No Known Activations