© 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. 22-GEMMASCOPE-RES-131K
    7. 128933
    Prev
    Next
    INDEX
    Explanations

    type definitions

    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
    STALK
    -1.09
    ichern
    -1.02
    ние
    -0.99
    жение
    -0.97
    ICAN
    -0.96
    椋
    -0.95
    橢
    -0.93
    鱂
    -0.91
     kritik
    -0.91
    书房
    -0.90
    POSITIVE LOGITS
    4
    1.03
    AK
    0.99
    J
    0.92
    Q
    0.91
    k
    0.89
     beschäftigt
    0.86
     distintas
    0.85
    H
    0.85
     europeos
    0.84
    Z
    0.83
    Activations Density 0.035%

    No Known Activations