© 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. 5344
    Prev
    Next
    INDEX
    Explanations

    Edge, design, Besides

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

    structural markers of organized technical text—section headers, list/bullet separators, and other outline-style cues indicating topic shifts or labeled subsections.

    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_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
    窣
    0.24
    чности
    0.23
     algorith
    0.23
     oppos
    0.23
    зин
    0.23
     worksheet
    0.22
    arrants
    0.22
    合物
    0.22
    שוט
    0.21
     wills
    0.21
    POSITIVE LOGITS
    前者
    0.25
    𝐊
    0.25
    幇
    0.25
     situatie
    0.24
     канторы
    0.23
     생각
    0.22
    ![](
    0.22
     কথাটা
    0.21
     الحالة
    0.21
     अनन्या
    0.21
    Activations Density 1.336%

    No Known Activations