© 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. 34-GEMMASCOPE-RES-131K
    7. 56742
    Prev
    Next
    INDEX
    Explanations

    violence against women and children

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Warburton
    -0.77
     kettle
    -0.76
     arthur
    -0.75
    AVL
    -0.72
    Bottle
    -0.72
    gging
    -0.70
    分け
    -0.70
     metabolism
    -0.70
     PropTypes
    -0.69
     Lepto
    -0.68
    POSITIVE LOGITS
     mutil
    1.24
     girls
    0.94
     Mädchen
    0.93
     mutilated
    0.90
     uncut
    0.88
     intact
    0.88
    ctice
    0.87
     UNICEF
    0.86
    UNICEF
    0.85
     Harmful
    0.84
    Activations Density 0.013%

    No Known Activations