© 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. 98891
    Prev
    Next
    INDEX
    Explanations

    template declarations with type parameters

    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
     PÅ
    -1.73
     viu
    -1.63
     playera
    -1.63
    🧏
    -1.61
     textil
    -1.59
     SEMESTER
    -1.58
     stund
    -1.51
     propiet
    -1.49
     dadas
    -1.48
     quella
    -1.46
    POSITIVE LOGITS
    ’
    2.17
    d
    1.78
     špec
    1.76
     that
    1.65
     kuitenkin
    1.62
     čier
    1.52
     or
    1.51
     rých
    1.48
     skuto
    1.45
     when
    1.45
    Activations Density 0.007%

    No Known Activations