© 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. 213243
    Prev
    Next
    INDEX
    Explanations

    victims were, cities/airports, yourself and

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

    arrest, number, recipes

    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
    Negative Logits
    輙
    0.59
    archical
    0.56
     január
    0.54
    pushButton
    0.53
     ähm
    0.53
    辄
    0.52
    onik
    0.52
    punkte
    0.51
    щика
    0.50
     Jangan
    0.50
    POSITIVE LOGITS
    College
    0.48
    Grant
    0.47
     verified
    0.46
    FC
    0.45
    Greg
    0.44
     jewelry
    0.44
    /
    0.44
    Consent
    0.43
    Rep
    0.43
    Crow
    0.43
    Activations Density 0.000%

    No Known Activations