© 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. 41363
    Prev
    Next
    INDEX
    Explanations

    code identifiers and abbreviations

    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
    鋮
    -3.17
    鄜
    -3.03
    ～。
    -2.91
     tillgäng
    -2.80
     särskilt
    -2.77
    屜
    -2.72
    戬
    -2.69
    蹀
    -2.69
    鹂
    -2.61
    ꯹
    -2.61
    POSITIVE LOGITS
    ?"
    3.95
    (
    3.22
    *
    3.09
    "—
    2.72
    {
    2.59
    <
    2.56
     has
    2.53
    As
    2.52
    >
    2.42
     travaille
    2.38
    Activations Density 0.147%

    No Known Activations