© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15740
    Prev
    Next
    INDEX
    Explanations

    names of sources following 'from'

    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
     Océ
    -1.77
     merke
    -1.56
     schuhe
    -1.56
     nuo
    -1.56
     maksi
    -1.55
    涠
    -1.53
     Femme
    -1.48
    獁
    -1.48
    裃
    -1.47
     dehors
    -1.46
    POSITIVE LOGITS
     –
    1.68
    0
    1.63
     of
    1.63
    );
    1.49
     just
    1.45
     time
    1.44
     support
    1.39
     —
    1.38
    \
    1.32
     only
    1.28
    Activations Density 0.053%

    No Known Activations