© 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. 58804
    Prev
    Next
    INDEX
    Explanations

    separator punctuation

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

    The neuron activates on dash‐style punctuation sequences (e.g. hyphens, en-dashes, and em-dashes used as separators).

    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
    除了
    -2.31
    啭
    -1.99
    ᚷ
    -1.99
     发型
    -1.95
    新的
    -1.94
     titolata
    -1.89
    需要
    -1.88
     addirittura
    -1.87
     hohe
    -1.86
    ہ
    -1.83
    POSITIVE LOGITS
     of
    2.23
    ⢓
    1.80
     they
    1.77
    ’
    1.75
     британ
    1.71
    a
    1.58
    市の
    1.55
    シルバー
    1.54
     "
    1.53
     then
    1.51
    Activations Density 0.017%

    No Known Activations