© 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. 7589
    Prev
    Next
    INDEX
    Explanations

    highlighting differences

    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
     Даже
    -1.50
     Since
    -1.46
     Unless
    -1.45
     Regardless
    -1.43
     Nonetheless
    -1.41
     This
    -1.38
     Ironically
    -1.32
     їх
    -1.31
     также
    -1.29
     også
    -1.29
    POSITIVE LOGITS
     everyone
    1.95
     unlike
    1.79
    秾
    1.73
     anyone
    1.71
     vidas
    1.69
     lança
    1.69
    殽
    1.64
    怍
    1.63
    䜣
    1.63
     the
    1.59
    Activations Density 0.009%

    No Known Activations