© 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. 73422
    Prev
    Next
    INDEX
    Explanations

    declarations and identifiers

    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
     last
    -1.02
    Бележки
    -1.02
    之前
    -0.94
     first
    -0.93
    toContain
    -0.93
    enumii
    -0.92
     previous
    -0.92
     back
    -0.90
    よろしくお願いします
    -0.90
     pregă
    -0.89
    POSITIVE LOGITS
    臬
    1.13
     monitoring
    1.05
     GaAs
    1.04
     monitored
    1.01
     Fácil
    0.98
     estes
    0.98
     chré
    0.97
     values
    0.97
    vati
    0.96
     DATOS
    0.96
    Activations Density 0.048%

    No Known Activations