© 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. 205088
    Prev
    Next
    INDEX
    Explanations

    uric acid, coming doom, physician

    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
    政府采购
    0.43
     Fulbright
    0.39
    ﻴ
    0.39
    絭
    0.38
     ጥቅ
    0.38
     பச
    0.38
     Vis
    0.37
     [[
    0.37
     আব
    0.37
    膚
    0.37
    POSITIVE LOGITS
     언급
    0.38
    ensä
    0.38
     ইসলামাবাদ
    0.37
    蜿
    0.36
    拉丁
    0.36
    alit
    0.35
    ின்ன
    0.35
     دکھائی
    0.35
    ולוג
    0.35
     Drop
    0.34
    Activations Density 0.000%

    No Known Activations