© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78174
    Prev
    Next
    INDEX
    Explanations

    people and places

    np_acts-logits-general · gemini-2.5-flash-lite

    Nations, metals, hazard, mamá

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ヤ
    0.44
    his
    0.44
    ہے
    0.43
    シェ
    0.42
    整備
    0.42
    presumably
    0.42
     mitigate
    0.42
    Forg
    0.41
     quell
    0.41
    둔
    0.41
    POSITIVE LOGITS
     Rajasthan
    0.54
     Labour
    0.50
     Bharat
    0.50
     Colchester
    0.50
     Weddings
    0.49
     Brides
    0.48
     Salford
    0.48
     Varanasi
    0.47
     Manipur
    0.46
     İzmir
    0.46
    Activations Density 0.001%

    No Known Activations