© 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. 62917
    Prev
    Next
    INDEX
    Explanations

    desk, reception, cashier, hospitality

    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
     reactor
    -0.84
    кои
    -0.78
     AS
    -0.74
    CHOS
    -0.74
     Polar
    -0.74
     déclaré
    -0.74
    Ws
    -0.74
     taxi
    -0.73
     store
    -0.71
    ität
    -0.70
    POSITIVE LOGITS
     desk
    2.30
    desk
    1.95
     DESK
    1.91
     Desk
    1.77
     desks
    1.70
    Desk
    1.55
     manned
    1.38
    DESK
    1.31
    manned
    1.22
     clerks
    1.08
    Activations Density 0.019%

    No Known Activations