© 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. 33603
    Prev
    Next
    INDEX
    Explanations

    nearby locations

    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
     with
    -1.35
    peka
    -1.10
    jda
    -1.01
    rogens
    -1.01
    THING
    -0.97
    的是
    -0.96
    terbury
    -0.95
     prefeito
    -0.95
    程度
    -0.94
     século
    -0.93
    POSITIVE LOGITS
     nearby
    1.50
     local
    1.41
     my
    1.27
     najbli
    1.26
     setempat
    1.25
     ibunya
    1.19
     okolí
    1.16
     vicinity
    1.15
     convenient
    1.14
    hésite
    1.11
    Activations Density 0.038%

    No Known Activations