© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25447
    Prev
    Next
    INDEX
    Explanations

    web, net, ws, xml

    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
    に行って
    -1.37
     asegurado
    -1.34
     and
    -1.31
    づけ
    -1.31
     destacado
    -1.30
     confirmado
    -1.25
    ところは
    -1.24
     a
    -1.23
    cautions
    -1.22
     fisuras
    -1.21
    POSITIVE LOGITS
    0
    1.66
     вместо
    1.50
    1.48
    を
    1.39
    7
    1.37
    と
    1.34
    DESCRIPCIÓN
    1.34
    3
    1.29
    -
    1.27
    ;
    
    1.27
    Activations Density 0.001%

    No Known Activations