© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34456
    Prev
    Next
    INDEX
    Explanations

    fork

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

    The neuron fires on occurrences of the token “fork,” marking references to forking (e.g. the fork system call or “Fork” in metadata).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ↵
    -2.94
    {
    -2.42
     \
    -2.28
    *
    -2.22
    鱟
    -2.11
     you
    -2.09
     to
    -2.08
     amounts
    -2.03
     тот
    -1.97
     vidas
    -1.95
    POSITIVE LOGITS
    獁
    2.75
    我先
    2.52
    媄
    2.28
     énergé
    2.25
     économiques
    2.23
     内衣
    2.19
    ⑉
    2.19
     绿色
    2.17
    Sito
    2.17
     半袖
    2.16
    Activations Density 0.008%

    No Known Activations