© 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. 15157
    Prev
    Next
    INDEX
    Explanations

    usernames before project descriptions

    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
    ,
    -1.56
     an
    -1.43
     as
    -1.42
     F
    -1.39
     P
    -1.34
     not
    -1.31
     T
    -1.29
     D
    -1.28
     S
    -1.28
     fifteen
    -1.26
    POSITIVE LOGITS
    𓁹
    1.68
     rayures
    1.68
     célè
    1.53
    〬
    1.53
     AspNetCore
    1.49
     coloriage
    1.48
     peindre
    1.43
    
    1.43
     marquer
    1.43
     arrêter
    1.43
    Activations Density 0.056%

    No Known Activations