© 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. 65969
    Prev
    Next
    INDEX
    Explanations

    colors and options

    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
     everything
    -1.16
     related
    -1.05
    付属品
    -1.02
    ndag
    -1.01
     المسؤول
    -0.99
     it
    -0.98
     σαν
    -0.96
    zellan
    -0.96
     nothing
    -0.95
     assistance
    -0.95
    POSITIVE LOGITS
     available
    1.72
     you
    1.34
     disponibles
    1.30
    Available
    1.30
    available
    1.25
     each
    1.21
    リエーション
    1.19
     options
    1.17
    łko
    1.17
     choose
    1.16
    Activations Density 0.030%

    No Known Activations