© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6379
    Prev
    Next
    INDEX
    Explanations

    knives and razor

    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_16_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
    ン
    0.69
    ین
    0.67
     Examples
    0.63
    DA
    0.61
     nantinya
    0.59
    VE
    0.59
    لی
    0.59
    نتی
    0.59
    <unused1051>
    0.59
     Iy
    0.58
    POSITIVE LOGITS
     knives
    0.79
     razor
    0.75
    刀
    0.72
     serviço
    0.71
     haircuts
    0.71
    '
    0.71
     shaving
    0.71
     slashing
    0.70
     Razor
    0.69
    手术
    0.67
    Activations Density 0.099%

    No Known Activations