© 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. 14796
    Prev
    Next
    INDEX
    Explanations

    file extensions and programming languages

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

    This neuron specializes in spotting punctuation and delimiter tokens (e.g. periods, equals signs, parentheses, braces) in code or config text.

    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
    -2.22
     this
    -1.98
     these
    -1.73
    ⇘
    -1.45
    (ﾟ
    -1.45
    今年の
    -1.45
    この記事
    -1.42
     vítimas
    -1.41
    ｼ
    -1.39
    ﾎ
    -1.35
    POSITIVE LOGITS
    _
    1.37
    了很多
    1.32
     cristianos
    1.31
     розовый
    1.29
    口碑
    1.28
     варианты
    1.27
     directivos
    1.24
    left
    1.23
     способов
    1.22
    1.22
    Activations Density 0.205%
    No Known Activations