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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118921
    Prev
    Next
    INDEX
    Explanations

    names and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Striped
    -0.80
    ầ
    -0.77
     registrations
    -0.75
    aplic
    -0.75
    ኝ
    -0.74
    laund
    -0.72
     Gifted
    -0.72
     projected
    -0.71
     striped
    -0.70
     Sari
    -0.70
    POSITIVE LOGITS
    dataclass
    0.79
     coughing
    0.79
    clientHeight
    0.79
     GL
    0.78
     وخ
    0.78
    orkin
    0.77
    breakable
    0.77
    mese
    0.76
    FlatButton
    0.75
     Khi
    0.74
    Activations Density 0.042%

    No Known Activations