© 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. 32588
    Prev
    Next
    INDEX
    Explanations

    medical treatment and patients

    np_acts-logits-general · gemini-2.5-flash-lite

    conversational and structural cues that introduce and organize a structured, step-by-step explanation or breakdown.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     siano
    0.37
    }$.
    0.36
    reachable
    0.36
    blic
    0.36
    vey
    0.35
    นั้น
    0.35
     noto
    0.35
    </em>
    0.35
     proport
    0.34
    avoir
    0.34
    POSITIVE LOGITS
     மருத்து
    0.39
     *)(
    0.38
     치료
    0.36
     phép
    0.34
    医生
    0.34
     лечение
    0.34
     ምግብ
    0.33
    患者
    0.33
    住院
    0.33
     மீட்ப
    0.33
    Activations Density 0.179%

    No Known Activations