© 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. 42149
    Prev
    Next
    INDEX
    Explanations

    explaining the details

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

    This neuron detects occurrences of the word “detail” (and its inflected forms like details, detailing).

    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
    {
    -2.06
    ↵↵
    -1.95
    "
    -1.93
    *
    -1.77
    骜
    -1.69
    <h2>
    -1.68
    javac
    -1.63
     reason
    -1.59
    ``
    -1.56
    iterranean
    -1.56
    POSITIVE LOGITS
    os
    2.16
    ar
    1.95
    Metode
    1.93
    Bety
    1.93
     Только
    1.93
    豋
    1.92
    Gön
    1.91
    Usos
    1.85
    Specifica
    1.76
    ists
    1.73
    Activations Density 0.019%

    No Known Activations