© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85962
    Prev
    Next
    INDEX
    Explanations

    Texas

    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
    '
    -3.78
    [
    -2.59
    --
    -2.48
    ?
    -2.41
    *
    -2.41
    \
    -2.39
     アウター
    -2.31
    (
    -2.30
    --"
    -2.27
    的做法
    -2.23
    POSITIVE LOGITS
    They
    2.61
     teilweise
    2.55
    鶲
    2.47
    텃
    2.47
    there
    2.44
    葙
    2.44
     Auffassung
    2.42
     untuk
    2.34
    There
    2.33
    委员会
    2.30
    Activations Density 0.011%

    No Known Activations