© 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. 36453
    Prev
    Next
    INDEX
    Explanations

    fitting shapes to models

    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
    ↵↵
    -2.52
    栴
    -2.38
    m
    -2.36
    沇
    -2.23
     sustancia
    -2.23
    祆
    -2.20
    鷓
    -2.13
    蜑
    -2.11
    靣
    -2.09
    ꦠ
    -2.09
    POSITIVE LOGITS
     When
    2.89
    」
    2.73
    [
    2.63
     daring
    2.52
    How
    2.52
    ・・・」
    2.47
     concernés
    2.41
     However
    2.36
     démocr
    2.36
    And
    2.34
    Activations Density 0.014%

    No Known Activations