© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86973
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     élas
    -2.36
     nettoy
    -2.34
     trajets
    -2.33
     récol
    -2.31
     refroid
    -2.28
     épar
    -2.23
     lèvres
    -2.23
    这么多
    -2.22
     matériaux
    -2.22
     réfrig
    -2.19
    POSITIVE LOGITS
     know
    2.55
     of
    2.28
     be
    2.19
     consider
    2.16
     never
    2.11
    er
    2.09
     have
    2.06
     not
    2.05
     in
    2.03
     ideally
    1.95
    Activations Density 0.011%

    No Known Activations