© 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. 72146
    Prev
    Next
    INDEX
    Explanations

    cinematography, sheath, undercut

    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
    ing
    -3.42
    汌
    -2.55
     
    -2.50
     :).
    -2.42
     Ahnung
    -2.39
     ‘
    -2.33
    橚
    -2.30
    他の
    -2.30
    .",
    -2.27
    .
    -2.25
    POSITIVE LOGITS
    ↑↑↑</
    2.78
    all
    2.47
    __))
    2.19
     體
    2.17
     sympathi
    2.17
    da
    2.16
    ER
    2.16
    دين
    2.13
    比如说
    2.11
     exacer
    2.09
    Activations Density 0.014%

    No Known Activations