© 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. 79466
    Prev
    Next
    INDEX
    Explanations

    titles of media and organizations

    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
    OLVED
    -0.91
    🚛
    -0.87
    Ladies
    -0.86
     Portugu
    -0.84
     `${
    -0.81
     céramique
    -0.80
    ?''
    -0.80
    Robertson
    -0.80
     vano
    -0.80
     sightseeing
    -0.80
    POSITIVE LOGITS
    the
    1.02
    gggg
    1.02
     Out
    0.90
     Our
    0.88
     fér
    0.84
     Soon
    0.84
     handeln
    0.83
     our
    0.82
    redient
    0.82
     retaining
    0.82
    Activations Density 0.054%

    No Known Activations