© 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. 105050
    Prev
    Next
    INDEX
    Explanations

    programming commands

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

    the function name "fopen" in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on code tokens that name file‐ or stream‐handling operations (e.g. fopen, fwrite, feof, chmod).

    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
     That
    -3.09
     It
    -3.06
     Actually
    -2.86
     From
    -2.83
     Surprisingly
    -2.73
     Much
    -2.72
     During
    -2.69
     Notably
    -2.64
     Mostly
    -2.63
     Through
    -2.59
    POSITIVE LOGITS
    癭
    2.81
     '
    2.63
    小孩子
    2.39
    小朋友
    2.34
    髕
    2.33
    戕
    2.30
    ⸪
    2.30
    '
    2.28
     conocidas
    2.25
     créé
    2.22
    Activations Density 0.003%

    No Known Activations