© 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. 16-GEMMASCOPE-2-RES-16K
    7. 656
    Prev
    Next
    INDEX
    Explanations

    killing and death

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

    death and killing

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

    death/killing

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ס
    0.92
    CB
    0.85
    са
    0.85
    ‌ای
    0.85
    TION
    0.84
    ي
    0.83
    CAT
    0.81
    TMP
    0.80
    T
    0.80
    ‌است
    0.80
    POSITIVE LOGITS
    at
    0.86
    死的
    0.79
     by
    0.71
     deaths
    0.70
     death
    0.69
     kill
    0.69
     I
    0.68
     killings
    0.68
     muerte
    0.66
     arme
    0.65
    Activations Density 0.669%

    No Known Activations