© 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. 105714
    Prev
    Next
    INDEX
    Explanations

    Juan followed by other names

    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
    ↵
    -3.03
    ’
    -2.81
    ”
    -2.77
    *
    -2.69
    ',
    -2.53
     -
    -2.52
    —
    -2.44
    朏
    -2.42
    {
    -2.41
    [
    -2.38
    POSITIVE LOGITS
    𓋼
    3.34
    ！！！”
    2.95
    鸶
    2.73
     帅气
    2.69
    荜
    2.67
    要在
    2.66
     mété
    2.61
    providedIn
    2.55
    秕
    2.53
     pérd
    2.50
    Activations Density 0.003%

    No Known Activations