© 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. 34-GEMMASCOPE-RES-131K
    7. 47078
    Prev
    Next
    INDEX
    Explanations

    listing locations separated by commas

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    蕻
    -1.45
    ();
    -1.25
    ()}>
    -1.23
     beautifully
    -1.22
     furia
    -1.21
     forno
    -1.20
     crea
    -1.20
     birra
    -1.19
     tranſ
    -1.19
     schuhe
    -1.18
    POSITIVE LOGITS
     rồng
    1.00
     all
    0.97
     In
    0.94
    整個
    0.94
     For
    0.93
     artful
    0.93
     Only
    0.93
     Perhaps
    0.91
     as
    0.90
     on
    0.90
    Activations Density 0.060%

    No Known Activations