© 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. 10-GEMMASCOPE-RES-131K
    7. 58475
    Prev
    Next
    INDEX
    Explanations

    game boards and grids

    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_10/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
    -1.60
    Coff
    -1.28
    思議
    -1.28
    (":");
    -1.24
     data
    -1.23
     out
    -1.23
     no
    -1.23
     große
    -1.23
     if
    -1.22
     substantial
    -1.22
    POSITIVE LOGITS
     calzado
    1.60
     colorés
    1.38
     pensées
    1.34
     mobiliario
    1.34
     acogedor
    1.31
    besos
    1.29
     evangé
    1.29
     haki
    1.27
     kitu
    1.26
     mueble
    1.22
    Activations Density 0.016%

    No Known Activations