© 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. 15696
    Prev
    Next
    INDEX
    Explanations

    technical report structure

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

    assistant-style, structured explanatory formatting and meta-reasoning sections (headings, lists, and breakdowns) in responses.

    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
     учун
    0.34
     मुखिया
    0.29
     dehuman
    0.29
     Loksatta
    0.28
     както
    0.28
     Ў
    0.28
     nomen
    0.27
     uchun
    0.27
     ነው።
    0.27
    fcast
    0.27
    POSITIVE LOGITS
    鐲
    0.35
     WHITE
    0.32
    WHITE
    0.31
     গঙ্গ
    0.31
    鲷
    0.29
     plasmids
    0.29
    Todd
    0.28
     mussels
    0.27
     lagoons
    0.27
    HILL
    0.27
    Activations Density 43.418%

    No Known Activations