© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23702
    Prev
    Next
    INDEX
    Explanations

    closing syntax punctuation

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

    The neuron fires on tokens containing digits or numeric literals (e.g. version numbers, numeric constants, or digit‐containing strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    士兵
    -0.78
     whistled
    -0.77
     erneut
    -0.75
     остается
    -0.75
    HeaderComponent
    -0.73
    thar
    -0.73
    かさ
    -0.73
    ysmal
    -0.72
    casal
    -0.71
    ستگی
    -0.71
    POSITIVE LOGITS
    '
    0.87
    ↵
    0.82
    $),
    0.77
     porcelaine
    0.76
    '],'
    0.75
    хим
    0.75
    venir
    0.75
     );
    0.73
    照明
    0.72
    jiri
    0.71
    Activations Density 0.101%

    No Known Activations