© 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. 20743
    Prev
    Next
    INDEX
    Explanations

    articulation agreements

    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
     bumps
    0.43
    Gos
    0.40
     ধরার
    0.39
     Turbulence
    0.38
     ders
    0.38
     Ties
    0.38
     Struggles
    0.38
    ㈤
    0.38
    ORDIN
    0.38
    ዛ
    0.38
    POSITIVE LOGITS
     Biblia
    0.41
     slid
    0.38
     طالب
    0.37
    谴
    0.37
     سنت
    0.36
    marginY
    0.34
    华
    0.34
    詮
    0.34
    लोत
    0.33
     dung
    0.33
    Activations Density 0.000%

    No Known Activations