© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21009
    Prev
    Next
    INDEX
    Explanations

    quick [service/info]

    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
    of
    -3.11
    等我
    -2.73
    {
    -2.61
    <
    -2.55
    on
    -2.53
    *
    -2.52
    烀
    -2.48
     sechs
    -2.47
     fün
    -2.47
    "
    -2.44
    POSITIVE LOGITS
    ⎙
    3.13
     fédé
    3.03
     решила
    3.00
     москва
    2.95
     аккура
    2.66
    ‪.‬‬
    2.63
    齮
    2.56
    蟶
    2.56
    鋮
    2.55
    媜
    2.52
    Activations Density 0.013%

    No Known Activations