© 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. 153189
    Prev
    Next
    INDEX
    Explanations

    pornography, obscenity, dissemination

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

    misleading advertising and content

    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
    classe
    0.48
     cenário
    0.45
     famí
    0.45
     vár
    0.44
     storico
    0.43
    身長
    0.43
     alguns
    0.43
    暌
    0.43
    terrain
    0.42
     dute
    0.42
    POSITIVE LOGITS
     pornography
    0.57
     অশ্লীল
    0.56
     dissemination
    0.54
     advertising
    0.52
     गलत
    0.52
     распростра
    0.52
     deleting
    0.50
     disseminating
    0.49
    删除
    0.49
     फैलाने
    0.49
    Activations Density 0.003%

    No Known Activations