© 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. 10-GEMMASCOPE-RES-131K
    7. 118925
    Prev
    Next
    INDEX
    Explanations

    direct speech indicators

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

    This neuron activates on dialogue‐tag verbs—i.e. words used to attribute speech (said, asks, hissed, drawled, admitted, etc.).

    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
     also
    -2.09
     também
    -1.69
     також
    -1.57
     también
    -1.55
    !
    -1.54
    nya
    -1.52
     также
    -1.52
     varje
    -1.43
     EACH
    -1.43
    '
    -1.39
    POSITIVE LOGITS
     before
    1.95
    notated
    1.86
     despite
    1.85
    是吗
    1.83
    しましたが
    1.63
     until
    1.61
    しますが
    1.60
    archical
    1.59
    identiality
    1.59
     not
    1.57
    Activations Density 0.003%

    No Known Activations