© 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. 106502
    Prev
    Next
    INDEX
    Explanations

    Academy Award

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ichtet
    -0.77
     helps
    -0.74
    acionais
    -0.73
     Planners
    -0.70
    Album
    -0.68
    Ingredientes
    -0.67
     barbecue
    -0.67
    몬
    -0.67
    如
    -0.67
    بود
    -0.67
    POSITIVE LOGITS
     Oscars
    2.13
     Oscar
    2.08
     Academy
    1.85
    Academy
    1.63
    Oscar
    1.61
     ACADEMY
    1.48
     oscar
    1.45
     academy
    1.40
     OSC
    1.34
     Óscar
    1.30
    Activations Density 0.026%

    No Known Activations