© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73163
    Prev
    Next
    INDEX
    Explanations

    error: GPGME error: No 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
     in
    -2.97
     on
    -2.03
     of
    -2.03
     will
    -1.90
     at
    -1.83
     In
    -1.82
     to
    -1.80
     M
    -1.80
     E
    -1.79
     A
    -1.77
    POSITIVE LOGITS
    ↵
    2.42
    ↵↵
    1.90
    퐼
    1.81
     almohada
    1.71
     cárcel
    1.71
     ventilación
    1.70
     vorhandenen
    1.69
     rebaj
    1.65
    </h2>
    1.64
     verschillende
    1.63
    Activations Density 0.093%

    No Known Activations