© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50252
    Prev
    Next
    INDEX
    Explanations

    violence and assault

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insidious
    0.45
    ိမ်
    0.45
     Banking
    0.43
    罪
    0.42
     금융
    0.42
    金融
    0.41
     banking
    0.40
    banking
    0.39
    comprom
    0.39
     compulsion
    0.39
    POSITIVE LOGITS
     beaten
    1.08
     beating
    1.07
     beat
    1.03
     मारपीट
    1.02
     पिटाई
    0.98
    毆
    0.96
     violence
    0.92
    殴
    0.90
    beat
    0.85
     Beat
    0.85
    Activations Density 0.088%

    No Known Activations