© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11452
    Prev
    Next
    INDEX
    Explanations

    list items in structured data

    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_22/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
    вила
    -0.81
    Assemb
    -0.80
    حيث
    -0.80
     CORNER
    -0.79
     جمع
    -0.79
    ₂,
    -0.79
     veía
    -0.78
     Gebir
    -0.78
    杯
    -0.78
     COMPAN
    -0.76
    POSITIVE LOGITS
     Lleg
    0.99
    まずは
    0.92
     first
    0.91
     followed
    0.89
    ựng
    0.86
     násled
    0.84
    展開
    0.84
    サンプル
    0.83
     первым
    0.82
     bénévoles
    0.82
    Activations Density 0.067%

    No Known Activations