© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    image size descriptors

    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
    wość
    -0.79
    <>
    -0.78
    racia
    -0.76
     lägga
    -0.76
    録画
    -0.76
     insure
    -0.75
    schuh
    -0.75
     Betty
    -0.75
    ವ
    -0.74
     Vainqueur
    -0.73
    POSITIVE LOGITS
     original
    1.32
     medium
    1.24
     originales
    1.09
    original
    1.08
    Large
    1.06
    Medium
    1.05
    Original
    1.04
     large
    1.04
    large
    1.02
     thumbnail
    1.02
    Activations Density 0.030%

    No Known Activations