© 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. 113970
    Prev
    Next
    INDEX
    Explanations

    extensively studied

    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
    籥
    -2.31
     tendo
    -1.97
    “
    -1.93
     a
    -1.91
    锨
    -1.84
    でご
    -1.81
     exclusivo
    -1.76
     vistos
    -1.75
    </i>
    -1.73
    спомина
    -1.72
    POSITIVE LOGITS
    m
    2.44
    ya
    1.98
    ā
    1.95
     $-$
    1.93
    i
    1.92
    ଃ
    1.91
     This
    1.91
     來
    1.80
     này
    1.79
    k
    1.77
    Activations Density 0.011%

    No Known Activations