© 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. 68509
    Prev
    Next
    INDEX
    Explanations

    not sure about

    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
     kabát
    -1.48
     své
    -1.47
     hicieron
    -1.41
     heut
    -1.35
     saisi
    -1.34
    rassing
    -1.33
    gyz
    -1.32
     espagnole
    -1.31
     rám
    -1.30
     constantemente
    -1.30
    POSITIVE LOGITS
    5
    1.98
    to
    1.79
    and
    1.61
    4
    1.61
    take
    1.59
    e
    1.56
    k
    1.55
    up
    1.53
    is
    1.53
    for
    1.52
    Activations Density 0.017%

    No Known Activations