© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11099
    Prev
    Next
    INDEX
    Explanations

    parentheses around code or definitions

    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
     decoracion
    -1.25
     specif
    -1.14
     diversos
    -1.12
     possam
    -1.11
    Pasos
    -1.07
     Redewendung
    -1.07
    嘥
    -1.07
     contrats
    -1.02
    迎来
    -1.01
     poderão
    -0.99
    POSITIVE LOGITS
     from
    2.06
     for
    1.63
     to
    1.59
     with
    1.37
     or
    1.30
     not
    1.30
     Really
    1.29
     EVERY
    1.28
     without
    1.20
     partially
    1.19
    Activations Density 0.009%

    No Known Activations