© 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. 10-GEMMASCOPE-RES-131K
    7. 83652
    Prev
    Next
    INDEX
    Explanations

    perceptual qualities, psychotic symptoms

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     keja
    -2.69
    )$
    -2.58
     If
    -2.58
    ));
    -2.45
    $,
    -2.44
    ();
    -2.39
     )
    -2.33
    -2.33
    国家的
    -2.33
    //
    -2.31
    POSITIVE LOGITS
     momentous
    2.95
    搋
    2.86
    摸了
    2.83
     delightfully
    2.72
    ῞
    2.69
    EVERY
    2.66
     deliciously
    2.66
    ‘
    2.66
    “
    2.66
     wonderfully
    2.56
    Activations Density 0.001%

    No Known Activations