© 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. 45564
    Prev
    Next
    INDEX
    Explanations

    qualify, qualifier, qualifications

    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
    ',
    -2.73
    ",
    -2.42
    ),
    -2.08
    ’
    -2.08
    杁
    -2.06
    鐿
    -2.03
    %,
    -2.02
     =
    -2.00
    ="
    -1.98
     -
    -1.95
    POSITIVE LOGITS
    ligator
    2.25
    isers
    2.19
     剤
    2.13
     estekak
    2.09
    国庆
    2.08
    itisation
    2.06
    魮
    2.05
    諼
    2.03
    冧
    2.03
     gustan
    1.98
    Activations Density 0.000%

    No Known Activations