© 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. 22-GEMMASCOPE-RES-131K
    7. 24994
    Prev
    Next
    INDEX
    Explanations

    referring to things

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    добно
    -1.02
    鵟
    -0.99
     élastique
    -0.99
    <bos>
    -0.98
    leneck
    -0.93
    athered
    -0.93
     sitesinde
    -0.93
     démoc
    -0.92
    ToDate
    -0.91
    cún
    -0.91
    POSITIVE LOGITS
     of
    1.19
     size
    1.18
     whose
    1.07
     its
    1.05
     ours
    0.98
    代の
    0.92
     strconv
    0.91
     full
    0.90
     if
    0.89
    ડ
    0.88
    Activations Density 0.234%

    No Known Activations