© 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. 26358
    Prev
    Next
    INDEX
    Explanations

    urls with articles or specific paths

    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
    卻
    -1.01
     even
    -0.98
    However
    -0.97
     some
    -0.93
     one
    -0.93
     on
    -0.93
    Выводы
    -0.90
     two
    -0.90
     einander
    -0.90
     escuchadas
    -0.89
    POSITIVE LOGITS
     acquist
    1.11
     différentes
    1.10
     различные
    1.09
     différents
    1.06
    inement
    1.06
     gâ
    1.05
    different
    1.05
    jspx
    1.04
     personalización
    1.03
    notated
    1.02
    Activations Density 0.021%

    No Known Activations