© 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. 47285
    Prev
    Next
    INDEX
    Explanations

    end of statement

    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
     on
    -1.76
     if
    -1.73
     during
    -1.70
     more
    -1.70
     for
    -1.66
     then
    -1.63
     at
    -1.63
     now
    -1.61
     During
    -1.59
     without
    -1.57
    POSITIVE LOGITS
     ſeveral
    1.45
     uſ
    1.38
     áng
    1.34
     ་
    1.34
     protéger
    1.34
     molte
    1.31
     faciliter
    1.30
     sooo
    1.30
     plusieurs
    1.27
     favoriser
    1.27
    Activations Density 0.033%

    No Known Activations