© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4874
    Prev
    Next
    INDEX
    Explanations

    AI disclaimers

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

    statements where the speaker issues a disclaimer identifying themselves as an AI and noting limitations or non-advisory status.

    oai_token-act-pair · gpt-5Triggered by @yooniel31
    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
     flown
    0.36
     Đ
    0.32
     floated
    0.32
    h
    0.31
     έτσι
    0.31
     hung
    0.30
     in
    0.30
    vär
    0.30
     anno
    0.29
     _{\
    0.29
    POSITIVE LOGITS
     допомо
    0.32
    XYGEN
    0.31
     plagiarism
    0.31
     choisir
    0.30
     உதவி
    0.30
     الفريق
    0.29
    团队
    0.29
    cheidung
    0.29
    INGS
    0.29
    ‧
    0.29
    Activations Density 0.078%

    No Known Activations