© 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. 10-GEMMASCOPE-RES-131K
    4. 65307
    Prev
    Next
    INDEX
    Explanations

    city and state officials

    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
    those
    -1.55
    鸱
    -1.52
    others
    -1.52
    𖧵
    -1.50
     begre
    -1.47
     contiennent
    -1.46
     carrefour
    -1.45
     fallu
    -1.43
     difficiles
    -1.41
     nostal
    -1.40
    POSITIVE LOGITS
     new
    1.98
     at
    1.90
     wide
    1.87
     and
    1.73
     after
    1.73
    wide
    1.69
     ochrony
    1.66
     four
    1.63
     three
    1.63
     harmful
    1.60
    Activations Density 0.095%

    No Known Activations