© 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. 17547
    Prev
    Next
    INDEX
    Explanations

    production and path

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

    structured documentation and explanatory formatting cues—like docstrings, section headers, notes, and example/usage markers—in technical or guide-style text.

    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
    ུ་
    0.44
     ساده
    0.44
    denes
    0.41
     Sixteen
    0.41
    cfe
    0.40
     שלו
    0.40
     психо
    0.39
    त्याने
    0.39
     возбу
    0.39
    vede
    0.39
    POSITIVE LOGITS
     ik
    0.42
    َس
    0.42
    BM
    0.41
    อกจาก
    0.41
     tabb
    0.40
     innym
    0.39
     możemy
    0.39
    จาก
    0.39
     airst
    0.39
    镳
    0.39
    Activations Density 2.580%

    No Known Activations