© 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. 129082
    Prev
    Next
    INDEX
    Explanations

    code snippets 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
     profils
    -1.07
     avantages
    -1.02
     autres
    -1.02
     contextes
    -1.00
     boucles
    -0.96
     huiles
    -0.94
     morceaux
    -0.93
    🎒
    -0.93
    cropping
    -0.93
     trajets
    -0.92
    POSITIVE LOGITS
    ingresso
    1.07
    Меня
    0.98
    Many
    0.97
     people
    0.96
    Това
    0.96
    Two
    0.96
    appartamento
    0.96
     places
    0.96
    Sinopse
    0.95
    Three
    0.94
    Activations Density 0.001%

    No Known Activations