© 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. 62452
    Prev
    Next
    INDEX
    Explanations

    description:

    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
    estroyer
    -0.93
    落とし
    -0.92
    क्या
    -0.91
    𝑌
    -0.90
    ={<
    -0.88
     χ
    -0.86
     peculiar
    -0.83
    OCH
    -0.83
    ffe
    -0.82
     Suomen
    -0.82
    POSITIVE LOGITS
     of
    1.89
    :
    0.99
     not
    0.97
     siitä
    0.96
    ของ
    0.96
     from
    0.95
     coming
    0.94
     HERE
    0.91
     của
    0.90
     courtesy
    0.90
    Activations Density 0.078%

    No Known Activations