© 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. 98852
    Prev
    Next
    INDEX
    Explanations

    color followed by a noun

    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
     ,‬
    -1.52
     is
    -1.35
     unbekannt
    -1.34
     geringe
    -1.34
    </em>
    -1.33
     which
    -1.32
    豋
    -1.31
    .
    -1.30
     predominantly
    -1.30
    usually
    -1.30
    POSITIVE LOGITS
     new
    1.70
     any
    1.63
     застосування
    1.55
    iteritems
    1.48
     those
    1.47
     навіть
    1.44
     with
    1.40
    淦
    1.40
     große
    1.40
     він
    1.39
    Activations Density 0.046%

    No Known Activations