© 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. 86091
    Prev
    Next
    INDEX
    Explanations

    drinking bleach dangerous events

    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
    yla
    0.53
    the
    0.51
    1
    0.50
    nya
    0.50
     centerpiece
    0.49
    rights
    0.49
    push
    0.48
     गड़ब
    0.48
     Hal
    0.48
    shot
    0.48
    POSITIVE LOGITS
    ק
    0.57
    최
    0.53
    ת
    0.50
    ز
    0.50
    ית
    0.48
    يك
    0.48
    מ
    0.48
     NAA
    0.47
    ט
    0.47
     xưa
    0.47
    Activations Density 0.000%

    No Known Activations