© 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. 34265
    Prev
    Next
    INDEX
    Explanations

    one X: explanation

    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
     также
    -1.21
     also
    -1.18
    Buna
    -1.09
     כבר
    -1.05
    también
    -1.04
    也将
    -1.02
     inoltre
    -1.02
     також
    -1.01
     мои
    -1.00
    噁
    -1.00
    POSITIVE LOGITS
     that
    1.16
     their
    1.14
    那就是
    1.11
     namely
    1.03
     whether
    0.94
     they
    0.93
     unless
    0.91
     unequivocally
    0.91
    好不好
    0.91
     which
    0.90
    Activations Density 0.033%

    No Known Activations