© 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. 79502
    Prev
    Next
    INDEX
    Explanations

    Kumar Kelker

    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
     Moul
    -0.78
    IMAN
    -0.76
    weiter
    -0.73
    immel
    -0.72
     ensalada
    -0.71
     Wanderers
    -0.71
     cursos
    -0.71
     ramps
    -0.70
     BODY
    -0.69
    OuterAlt
    -0.69
    POSITIVE LOGITS
     něco
    0.74
    êtements
    0.71
     neither
    0.71
     　　
    0.71
     coś
    0.70
    前の
    0.68
    parrot
    0.68
    unkt
    0.67
    filelist
    0.67
    onu
    0.66
    Activations Density 0.015%

    No Known Activations