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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9873
    Prev
    Next
    INDEX
    Explanations

    kill, kills, killing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     அதிகரி
    0.54
    +|\
    0.51
     förb
    0.51
     relaunch
    0.50
     فح
    0.49
    Redis
    0.49
    onResume
    0.49
     rebuilding
    0.48
     renewing
    0.48
     restarting
    0.48
    POSITIVE LOGITS
     kill
    1.98
     kills
    1.82
     killing
    1.80
    杀死
    1.77
    kill
    1.74
    killing
    1.63
    杀
    1.63
    KILL
    1.62
    殺
    1.61
    Kill
    1.59
    Activations Density 0.267%

    No Known Activations