© 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. 30023
    Prev
    Next
    INDEX
    Explanations

    on_delete options

    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
    Chemicals
    -0.73
     anim
    -0.71
    Hubert
    -0.69
    われました
    -0.69
    主意
    -0.68
    몫
    -0.68
    AREA
    -0.67
     markedly
    -0.66
    hæ
    -0.66
    átu
    -0.66
    POSITIVE LOGITS
    िया
    0.80
     conflicting
    0.78
     conflict
    0.78
    conflict
    0.77
    Conflict
    0.77
     stomach
    0.77
     chauffeur
    0.76
     Lio
    0.76
     רבי
    0.75
     vorne
    0.73
    Activations Density 0.012%

    No Known Activations