© 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. 5414
    Prev
    Next
    INDEX
    Explanations

    pytorch

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

    The neuron selectively activates on numeric tokens or numbers (dates, measurements, counts, etc.).

    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
     Ambient
    0.55
    opcode
    0.55
    +".
    0.53
     Shift
    0.50
     ."
    0.50
     Rope
    0.50
     Okan
    0.50
    Cookie
    0.50
    OpenFile
    0.50
     indien
    0.49
    POSITIVE LOGITS
     қ
    0.58
     γρα
    0.56
     टॉपर
    0.55
    zeige
    0.54
    꿈
    0.54
    ссмотрим
    0.54
     ხ
    0.53
     잡
    0.53
     розпо
    0.53
    روض
    0.53
    Activations Density 0.000%

    No Known Activations