© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4474
    Prev
    Next
    INDEX
    Explanations

    Chinese phrases and names

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

    references to formal named entities and citations—acronyms, organizations, case titles, sections, and other official proper nouns.

    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
    といった
    0.15
    高く
    0.14
    จาก
    0.14
    ंत्रिक
    0.14
    できる
    0.14
    同じ
    0.14
     _.
    0.14
     nDims
    0.14
    <unused2130>
    0.14
     যন্ত্র
    0.14
    POSITIVE LOGITS
    -
    0.22
    4
    0.20
    K
    0.19
    8
    0.16
    ти
    0.16
    5
    0.15
    7
    0.15
    āna
    0.15
    wood
    0.15
     I
    0.15
    Activations Density 8.621%

    No Known Activations