© 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. 16349
    Prev
    Next
    INDEX
    Explanations

    time markers and durations

    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
     postpone
    0.43
    LY
    0.40
     postponing
    0.39
    scrollTo
    0.38
    ly
    0.37
     tolerate
    0.37
     Mitigation
    0.36
    演
    0.36
     scrollTo
    0.35
    午
    0.35
    POSITIVE LOGITS
    Thirty
    0.79
     thirty
    0.77
     Thirty
    0.74
     sixty
    0.65
     treinta
    0.64
    thirty
    0.63
    Twenty
    0.63
     Twenty
    0.62
     seconds
    0.61
    三十
    0.61
    Activations Density 0.014%

    No Known Activations