© 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. 22-GEMMASCOPE-RES-131K
    7. 16549
    Prev
    Next
    INDEX
    Explanations

    default class or Q entry

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    퐿
    -1.69
    躂
    -1.66
     gemeenten
    -1.65
    푉
    -1.63
    ⧠
    -1.60
     ludzie
    -1.53
     También
    -1.47
    裥
    -1.45
     Projektu
    -1.45
     mehreren
    -1.44
    POSITIVE LOGITS
     in
    2.17
     (
    1.70
     are
    1.62
    ൎ
    1.38
     with
    1.38
     at
    1.34
     =='
    1.34
     doesn
    1.33
    ))))
    1.33
     produt
    1.31
    Activations Density 0.001%

    No Known Activations