© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26904
    Prev
    Next
    INDEX
    Explanations

    code comments and configuration

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

    The neuron spotlights lines beginning with hash‐style comment or directive markers (e.g. “#”, “##”, “#define”, “#undef”) in code or config files.

    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
     bepaalde
    -1.09
    也會
    -1.09
    氲
    -1.00
     assum
    -0.96
    に似
    -0.96
    êque
    -0.94
     другие
    -0.93
    ᱴ
    -0.93
    還會
    -0.93
     Urteil
    -0.91
    POSITIVE LOGITS
     made
    1.02
     in
    1.00
    🤙
    0.95
     but
    0.92
     on
    0.85
    😲
    0.85
    cream
    0.84
    [
    0.83
    一的
    0.83
    😟
    0.82
    Activations Density 0.020%

    No Known Activations