© 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. 34-GEMMASCOPE-RES-131K
    7. 78259
    Prev
    Next
    INDEX
    Explanations

    Query attention heads

    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
    zards
    -0.80
    codable
    -0.77
    追加
    -0.76
    gnar
    -0.76
     התח
    -0.75
     opzioni
    -0.75
     bundes
    -0.74
    cilla
    -0.72
     Cp
    -0.71
    Argument
    -0.71
    POSITIVE LOGITS
     attention
    1.29
     heads
    1.12
     query
    1.01
    query
    0.98
     Query
    0.94
    attention
    0.92
    getQuery
    0.89
    Query
    0.88
    heads
    0.87
     aten
    0.87
    Activations Density 0.000%

    No Known Activations