© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29709
    Prev
    Next
    INDEX
    Explanations

    individuals involved in violent incidents

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

    violent scenarios involving men and women

    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
    Not in Any Lists

    No Comments

    Negative Logits
     సమావేశ
    0.45
    런
    0.44
    쟤
    0.42
     युवाओं
    0.42
    會議
    0.42
     ముందుకు
    0.42
    に来
    0.42
     來
    0.41
    來
    0.41
     יו
    0.41
    POSITIVE LOGITS
     stabbed
    0.73
     fatally
    0.65
     killed
    0.64
     theft
    0.64
     قتل
    0.63
     abducted
    0.63
     died
    0.61
    قتل
    0.60
     kidnapped
    0.60
     thefts
    0.59
    Activations Density 0.045%

    No Known Activations