© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2944
    Prev
    Next
    INDEX
    Explanations

    graphic violence and gore

    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
    Not in Any Lists

    No Comments

    Negative Logits
    chenen
    -0.90
     fraudulent
    -0.90
     realice
    -0.85
     überweisen
    -0.84
    佈
    -0.83
    }
    -0.82
    MENTS
    -0.81
    ATION
    -0.81
     largeur
    -0.81
    tação
    -0.80
    POSITIVE LOGITS
     violence
    1.86
     gore
    1.78
     gory
    1.75
     violent
    1.62
     brutal
    1.59
     gruesome
    1.57
    violence
    1.55
     brutality
    1.51
    Violence
    1.51
     graphic
    1.46
    Activations Density 0.062%

    No Known Activations