© 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. 129237
    Prev
    Next
    INDEX
    Explanations

    only to a small degree

    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
    わん
    -1.10
     però
    -1.09
     opnieuw
    -1.09
     overzicht
    -1.09
     também
    -1.09
     néanmoins
    -1.07
     however
    -1.06
     velikost
    -1.05
     praktijk
    -1.05
     גם
    -1.05
    POSITIVE LOGITS
    V
    1.00
    R
    0.97
     barely
    0.96
    Such
    0.95
     only
    0.95
     use
    0.95
    G
    0.95
    M
    0.94
    W
    0.94
     will
    0.93
    Activations Density 0.037%

    No Known Activations