© 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. 98749
    Prev
    Next
    INDEX
    Explanations

    one 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
     from
    -2.72
     during
    -2.41
     for
    -2.36
    >
    -2.28
     to
    -2.28
     not
    -2.27
     with
    -2.16
     after
    -2.14
     as
    -2.11
     by
    -2.09
    POSITIVE LOGITS
    幛
    2.27
    ꜆
    2.17
     unending
    2.13
     extravag
    2.06
     mantenimiento
    2.02
    趿
    2.02
     plafon
    2.00
     THROUGH
    1.99
    푎
    1.98
    辇
    1.96
    Activations Density 0.019%

    No Known Activations