© 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. 44763
    Prev
    Next
    INDEX
    Explanations

    little waste or strain

    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
    !
    -1.66
    ℗
    -1.54
    ...
    -1.28
     GRATU
    -1.25
     and
    -1.18
    fashioned
    -1.17
    ldquo
    -1.16
    这一幕
    -1.16
     zui
    -1.15
     of
    -1.14
    POSITIVE LOGITS
     it
    1.89
     or
    1.76
    🩳
    1.45
     respaldo
    1.38
     others
    1.38
    หรือ
    1.37
    źródło
    1.36
    alım
    1.34
     aliviar
    1.34
     esclavos
    1.34
    Activations Density 0.364%

    No Known Activations