© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22888
    Prev
    Next
    INDEX
    Explanations

    collection of items or assets

    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
    Negative Logits
    $
    -1.81
     For
    -1.77
     in
    -1.55
     as
    -1.52
     with
    -1.46
    </i>
    -1.45
     lưng
    -1.42
     an
    -1.41
     geleden
    -1.40
     one
    -1.38
    POSITIVE LOGITS
     of
    2.28
    蹰
    1.65
     لعبة
    1.63
    Besitos
    1.58
     humeur
    1.58
    Zubereitung
    1.57
    Extrait
    1.55
     discurso
    1.55
    UDES
    1.55
    𓁹
    1.53
    Activations Density 0.068%

    No Known Activations