© 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. 32615
    Prev
    Next
    INDEX
    Explanations

    Tiger Woods

    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
     another
    -1.15
    reactstrap
    -1.09
    걱
    -1.08
     from
    -1.07
     now
    -1.04
    ");
    -1.04
     other
    -1.04
     anyone
    -1.03
     know
    -1.02
    あり
    -1.02
    POSITIVE LOGITS
     या
    1.20
    Bjs
    1.13
    伱
    1.09
     påvir
    1.09
    Hilsen
    1.05
     encuentros
    1.02
    因为他
    1.02
    やっと
    1.02
    lecte
    1.00
    贅沢
    1.00
    Activations Density 0.001%

    No Known Activations