© 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. 10-GEMMASCOPE-RES-131K
    7. 22254
    Prev
    Next
    INDEX
    Explanations

    variables in code snippets

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

    The neuron detects Perl variable‐sigil tokens (e.g. “$”, “@”) and other markers of variable usage in Perl code.

    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
    鹀
    -2.14
    ées
    -2.03
     děti
    -1.84
    鄠
    -1.84
    lying
    -1.82
    反应过来
    -1.82
    vertible
    -1.80
     jongen
    -1.78
    转头
    -1.76
     industrie
    -1.75
    POSITIVE LOGITS
    ’
    2.33
     also
    2.17
    需要
    2.16
     isn
    2.06
     only
    2.03
     doesn
    1.98
    也
    1.98
    等
    1.89
     not
    1.87
     does
    1.86
    Activations Density 0.014%

    No Known Activations