© 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. 6713
    Prev
    Next
    INDEX
    Explanations

    turn out to be

    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
     between
    -1.80
     of
    -1.63
    h
    -1.60
    f
    -1.59
     can
    -1.54
    ！
    -1.47
    '
    -1.45
    IA
    -1.44
    as
    -1.41
    ！”
    -1.41
    POSITIVE LOGITS
     savior
    1.63
    するのが
    1.60
     deseado
    1.52
    することも
    1.52
     perceber
    1.51
    ﾁ
    1.51
    זו
    1.48
    埼玉県
    1.48
     ouvir
    1.45
    uver
    1.45
    Activations Density 0.029%

    No Known Activations