© 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. 114037
    Prev
    Next
    INDEX
    Explanations

    * to From

    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
    0
    -1.82
     any
    -1.77
    )”
    -1.61
     Eröffnung
    -1.56
     morreu
    -1.55
     aprendizaje
    -1.54
     Absicht
    -1.52
    攵
    -1.51
     nasceu
    -1.50
    年は
    -1.49
    POSITIVE LOGITS
    originally
    1.74
    相同的
    1.69
    presumably
    1.68
    蹋
    1.68
     to
    1.68
    whose
    1.60
    </tfoot>
    1.55
    they
    1.52
    borderSide
    1.51
    from
    1.48
    Activations Density 0.042%

    No Known Activations