© 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. 15816
    Prev
    Next
    INDEX
    Explanations

    Nadia, Solar, Q: I

    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
     have
    -2.16
    孳
    -2.06
     dieser
    -1.77
    ୮
    -1.75
     didn
    -1.69
     consequently
    -1.67
    when
    -1.59
     causado
    -1.55
    崛
    -1.53
    );
    -1.52
    POSITIVE LOGITS
    妧
    1.85
     scattata
    1.79
     the
    1.74
     kimdir
    1.72
    
    1.71
     luxuri
    1.70
     anún
    1.70
    錞
    1.66
    Denne
    1.62
     ヌード
    1.61
    Activations Density 0.002%

    No Known Activations