© 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. 6508
    Prev
    Next
    INDEX
    Explanations

    pace and speed measurements

    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
     рік
    0.39
    期限
    0.38
     исторических
    0.38
     වෙන
    0.38
    ैटिन
    0.37
    鏁
    0.37
     وە
    0.36
    囟
    0.36
    高さ
    0.36
    ême
    0.36
    POSITIVE LOGITS
     pace
    0.93
    ペース
    0.75
     slowed
    0.73
     pacing
    0.73
     paces
    0.72
     slows
    0.69
     paced
    0.69
     slowing
    0.66
     ritmo
    0.66
     slower
    0.63
    Activations Density 0.011%

    No Known Activations