© 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. 65266
    Prev
    Next
    INDEX
    Explanations

    file path components

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

    The neuron flags code tokens that name or refer to files (e.g. “File”, “filename”, file paths, file formats, helpers, tags).

    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
    コチラ
    -1.05
    昞
    -1.04
     those
    -1.04
     businessmen
    -1.03
    镲
    -1.02
    ￤
    -0.98
    鷓
    -0.96
     createdBy
    -0.93
    禵
    -0.93
    様な
    -0.91
    POSITIVE LOGITS
     Then
    1.10
     Añade
    1.05
     Its
    1.02
    と
    1.02
    <bos>
    0.97
    ctuary
    0.96
     และ
    0.96
     is
    0.96
     ไม่
    0.95
     可以
    0.94
    Activations Density 0.145%

    No Known Activations