© 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. 61006
    Prev
    Next
    INDEX
    Explanations

    Hirsch and rock star

    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
     dünya
    -2.47
    浥
    -2.44
    熜
    -2.30
    哢
    -2.27
     作る
    -2.19
    实话
    -2.14
    生活的
    -2.14
    蕷
    -2.09
    有些不
    -2.09
    uestran
    -2.06
    POSITIVE LOGITS
    </strong>
    2.58
    ’
    2.45
    眼睛
    2.39
    &
    2.36
    $
    2.36
    <
    2.34
    {
    2.30
    of
    2.25
    o
    2.22
    婓
    2.19
    Activations Density 0.005%

    No Known Activations