© 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. 11924
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    跹
    0.43
    浔
    0.42
     laptops
    0.41
     Historical
    0.40
     Additional
    0.39
     tops
    0.39
     laptop
    0.39
    iyama
    0.39
     takers
    0.39
    广西
    0.38
    POSITIVE LOGITS
     reloj
    0.47
    言語
    0.43
    combin
    0.42
    orderHint
    0.42
    seeing
    0.41
     場合
    0.41
    ͅ
    0.40
     Riet
    0.39
    يس
    0.39
    orget
    0.39
    Activations Density 0.002%

    No Known Activations