© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29799
    Prev
    Next
    INDEX
    Explanations

    flashes of light

    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_40_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
     gyven
    0.40
     autonomia
    0.40
     Hamilton
    0.38
    reportBody
    0.38
    ྀ
    0.38
    dau
    0.38
    牰
    0.37
    честве
    0.37
     Buckeye
    0.37
     اوف
    0.36
    POSITIVE LOGITS
     flash
    1.69
    flash
    1.51
     Flash
    1.48
     flashes
    1.48
    Flash
    1.47
     flashed
    1.38
    闪
    1.37
     FLASH
    1.33
    FLASH
    1.30
     flashing
    1.23
    Activations Density 0.008%

    No Known Activations