© 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. 13879
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on numerical or measurement tokens—especially decimal numbers, distances, and unit-style expressions.

    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
    elessly
    0.84
    esan
    0.80
    idding
    0.73
     家
    0.73
    0.73
    ristmas
    0.71
    ロジー
    0.70
    ます
    0.70
     cancer
    0.68
    rą
    0.68
    POSITIVE LOGITS
     mevcut
    0.84
    kör
    0.77
    အ
    0.76
    멧
    0.71
    Τ
    0.71
    셜
    0.71
    Duc
    0.71
     oficiais
    0.70
     Aceh
    0.70
    Grady
    0.70
    Activations Density 0.000%

    No Known Activations