© 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. 21478
    Prev
    Next
    INDEX
    Explanations

    official documents and papers

    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
     "
    -1.60
    .'
    -1.40
     where
    -1.34
     has
    -1.29
     No
    -1.26
    [
    -1.25
    这些人
    -1.21
     only
    -1.20
    ."
    -1.18
     won
    -1.18
    POSITIVE LOGITS
    쩡
    1.58
    ATION
    1.56
     formalities
    1.53
    縂
    1.48
    垍
    1.46
    鯔
    1.45
     saken
    1.45
    icza
    1.45
    ttemberg
    1.40
    CurtirCurtir
    1.40
    Activations Density 0.038%

    No Known Activations