© 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. 31-GEMMASCOPE-2-RES-262K
    7. 13528
    Prev
    Next
    INDEX
    Explanations

    clopidogrel

    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_31_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
    財務
    0.47
    late
    0.40
     credited
    0.38
     expedite
    0.38
     taxed
    0.36
     taxable
    0.36
    폈
    0.36
     wealthier
    0.36
    額
    0.36
     mitigate
    0.35
    POSITIVE LOGITS
     powin
    0.61
     sollte
    0.59
     және
    0.57
     janë
    0.53
     seçenek
    0.53
     është
    0.51
     můžete
    0.51
    ที่มี
    0.51
     nämlich
    0.50
     помимо
    0.49
    Activations Density 0.001%

    No Known Activations