© 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. 128050
    Prev
    Next
    INDEX
    Explanations

    own choices and lives

    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
    ,
    -1.77
    '
    -1.66
    e
    -1.55
    a
    -1.45
    te
    -1.35
    骤
    -1.34
     autre
    -1.33
     it
    -1.33
    l
    -1.31
    its
    -1.27
    POSITIVE LOGITS
     їх
    1.63
     عندما
    1.48
    tarta
    1.47
    　↓
    1.44
     их
    1.41
     advirtió
    1.41
     jejich
    1.39
     применя
    1.38
     mereka
    1.37
     quelli
    1.34
    Activations Density 0.144%

    No Known Activations