© 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. 136321
    Prev
    Next
    INDEX
    Explanations

    policy violation responses

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

    Finds assistant messages that state whether a user request violates policy or otherwise explain content-moderation / policy compliance.

    oai_token-act-pair · gpt-5-miniTriggered 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
     दट
    0.45
    ViewSet
    0.44
     ViewBag
    0.43
     //}
    0.42
     받는
    0.42
     ওভারে
    0.41
     pertence
    0.41
     yazd
    0.40
    㭋
    0.40
    るので
    0.40
    POSITIVE LOGITS
    最も
    0.48
    f
    0.47
    ק
    0.46
     innocuous
    0.45
    guan
    0.45
    ファイル
    0.44
     או
    0.43
    Não
    0.43
    (.
    0.43
    文件
    0.42
    Activations Density 0.005%

    No Known Activations