© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35494
    Prev
    Next
    INDEX
    Explanations

    what should or can be

    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
     savon
    -1.29
     farine
    -1.07
     vinaigre
    -1.05
     moule
    -1.00
    Литература
    -0.94
     mondial
    -0.94
     sirop
    -0.94
     maux
    -0.93
    If
    -0.93
     lampe
    -0.92
    POSITIVE LOGITS
     versus
    1.55
     vs
    1.27
     what
    1.15
     whether
    1.06
     those
    1.05
     really
    1.03
     how
    1.02
    かどうか
    1.02
     not
    1.00
    是否
    0.98
    Activations Density 0.038%

    No Known Activations