© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11662
    Prev
    Next
    INDEX
    Explanations

    code imports

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

    The neuron detects numeric/specification tokens—numbers, measurements, prices, and related labels—in product or property listing–style contexts.

    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_24_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
     $\{(
    0.64
    ন্ড
    0.60
     cuyos
    0.59
     sicuro
    0.57
     conced
    0.56
     waahanga
    0.56
     domeni
    0.56
     múlti
    0.55
     başına
    0.55
    .
    0.54
    POSITIVE LOGITS
    storms
    0.74
     Bathurst
    0.67
     द्रव
    0.66
     Beatles
    0.65
     Confederate
    0.65
     Labrador
    0.64
     mildew
    0.64
     Bigfoot
    0.64
     Có
    0.64
     Eastwood
    0.63
    Activations Density 0.049%

    No Known Activations