© 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. 127601
    Prev
    Next
    INDEX
    Explanations

    hypothetical counterfactual conditions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    oted
    -1.41
    city
    -1.41
    </h2>
    -1.38
    鲧
    -1.38
     $>
    -1.37
    .},
    -1.36
    ",
    -1.35
    bility
    -1.34
    ophones
    -1.33
    the
    -1.32
    POSITIVE LOGITS
     If
    1.82
    If
    1.64
     it
    1.62
    teatro
    1.50
    
    1.41
     înal
    1.34
     réalisés
    1.34
     цього
    1.34
     Someone
    1.32
     Would
    1.31
    Activations Density 0.016%

    No Known Activations