© 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. 38361
    Prev
    Next
    INDEX
    Explanations

    involved in or with

    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
    '
    -1.99
    </h5>
    -1.72
     prób
    -1.63
    9
    -1.61
    0
    -1.61
    4
    -1.58
    3
    -1.54
     西
    -1.52
     utiliser
    -1.49
     parfois
    -1.49
    POSITIVE LOGITS
    </strong>
    1.91
     of
    1.88
     involved
    1.64
    s
    1.60
    潆
    1.57
     Involved
    1.56
    ྕ
    1.55
     excavations
    1.48
    県の
    1.43
     tuss
    1.43
    Activations Density 0.019%

    No Known Activations