© 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. 45575
    Prev
    Next
    INDEX
    Explanations

    proper nouns and places

    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
     of
    -2.17
    p
    -2.09
    to
    -1.93
    j
    -1.87
    of
    -1.85
    ber
    -1.85
    z
    -1.83
    em
    -1.76
    ang
    -1.74
    or
    -1.73
    POSITIVE LOGITS
    converse
    1.66
     your
    1.64
    <bos>
    1.55
    bracelet
    1.54
     voeding
    1.53
     medewerkers
    1.52
     verkoop
    1.51
     okru
    1.50
     sillas
    1.44
    leopard
    1.42
    Activations Density 0.121%

    No Known Activations