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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85043
    Prev
    Next
    INDEX
    Explanations

    Go package/function names

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

    This neuron fires on numeric literals in code (e.g. integer or floating-point constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -2.20
    \
    -1.75
     варианты
    -1.68
    л
    -1.66
    ،
    -1.65
    EdgeInsets
    -1.56
     abhor
    -1.55
    釓
    -1.55
     know
    -1.53
    ༒
    -1.53
    POSITIVE LOGITS
     These
    1.55
     and
    1.53
     jajaran
    1.52
     This
    1.48
    minton
    1.48
    streak
    1.39
     without
    1.38
     but
    1.38
     from
    1.38
     akhir
    1.36
    Activations Density 0.001%

    No Known Activations