© 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. 3434
    Prev
    Next
    INDEX
    Explanations

    definitions and names

    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
     for
    -1.00
     there
    -0.98
     you
    -0.94
     tech
    -0.93
     only
    -0.83
     filme
    -0.82
     What
    -0.82
     some
    -0.82
     Data
    -0.82
     both
    -0.81
    POSITIVE LOGITS
     Pokud
    1.05
     afectado
    1.04
    aites
    1.02
     perguntas
    0.99
     différentes
    0.99
    ומר
    0.97
     comportamento
    0.96
     znaczy
    0.96
    icat
    0.95
     MAKES
    0.95
    Activations Density 0.006%

    No Known Activations