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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15582
    Prev
    Next
    INDEX
    Explanations

    act of killing

    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_31_width_262k_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
     বিষয়ে
    0.57
     undergone
    0.57
     বিষয়ে
    0.55
    ס
    0.54
    opération
    0.53
     adı
    0.53
     zuletzt
    0.52
    attiyam
    0.52
    etar
    0.52
     acknowledges
    0.50
    POSITIVE LOGITS
     killing
    0.99
     kill
    0.98
    殺
    0.85
    killing
    0.82
     giết
    0.80
     killings
    0.80
     Killing
    0.78
     KILL
    0.78
    Kill
    0.77
     kills
    0.76
    Activations Density 0.035%

    No Known Activations