© 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. 22-GEMMASCOPE-RES-131K
    7. 39846
    Prev
    Next
    INDEX
    Explanations

    code structure and metadata

    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
     banane
    -1.20
     hanggang
    -1.14
     いる
    -1.08
    ̗
    -1.07
     natin
    -1.05
     SITY
    -1.04
     farine
    -1.04
    moine
    -1.03
    Ո
    -1.03
     gorą
    -1.02
    POSITIVE LOGITS
     Эти
    1.27
     trug
    1.04
    Dislikes
    0.98
     sufren
    0.95
    These
    0.95
     essas
    0.95
    pulseira
    0.95
    嫖
    0.93
    ();*/
    0.93
     again
    0.93
    Activations Density 0.001%

    No Known Activations