© 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. 67876
    Prev
    Next
    INDEX
    Explanations

    select, filter, promote, aids, blog, implemented

    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
     arguably
    -1.33
     extravagant
    -1.27
     also
    -1.27
     made
    -1.26
     ultimately
    -1.23
    Dto
    -1.21
     changes
    -1.20
    قامت
    -1.20
     changed
    -1.19
     will
    -1.18
    POSITIVE LOGITS
     Conſ
    1.41
    梛
    1.34
     soooo
    1.32
    ろん
    1.31
    curacy
    1.28
    鶿
    1.27
     magnific
    1.27
     некото
    1.26
     sorprender
    1.23
    starting
    1.21
    Activations Density 0.323%

    No Known Activations