© 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. 32951
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by states

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Tuber
    -1.34
    蒻
    -1.34
    tubers
    -1.33
    ridescent
    -1.21
    Ayrıca
    -1.19
    ighed
    -1.18
    (‘
    -1.18
    (“
    -1.17
    Özel
    -1.16
    ggy
    -1.13
    POSITIVE LOGITS
     is
    2.14
     cannot
    2.11
     should
    2.03
     could
    1.95
     may
    1.91
     are
    1.90
     must
    1.85
     not
    1.77
     would
    1.66
     didn
    1.56
    Activations Density 0.019%

    No Known Activations