© 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. 6673
    Prev
    Next
    INDEX
    Explanations

    all the way to

    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
     Также
    -1.84
     („
    -1.70
    _
    -1.69
     любых
    -1.65
     ſ
    -1.58
     übertragen
    -1.53
     
    -1.53
     भी
    -1.48
    尽量
    -1.48
    FontAwesomeIcon
    -1.48
    POSITIVE LOGITS
    呦
    1.75
    અ
    1.64
    enheim
    1.64
    ))$.
    1.60
    寵
    1.57
    આ
    1.57
    mudah
    1.57
    胛
    1.56
     ".";
    1.56
     our
    1.55
    Activations Density 0.006%

    No Known Activations