© 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. 74976
    Prev
    Next
    INDEX
    Explanations

    suitability and physical fit

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specifically detects occurrences of the substring “fit” in any context (e.g. in “def fit,” “helmet fit,” “fit shapes,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    鱻
    -2.50
    m
    -2.48
    祆
    -2.47
    蜑
    -2.47
     現貨
    -2.47
    靣
    -2.42
    獁
    -2.39
    栴
    -2.34
    ꦠ
    -2.33
    ￤
    -2.31
    POSITIVE LOGITS
     When
    3.33
    [
    3.14
     daring
    2.92
     concernés
    2.73
    How
    2.72
     cuando
    2.72
     However
    2.70
    」
    2.55
    At
    2.55
    Still
    2.48
    Activations Density 0.013%

    No Known Activations