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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8291
    Prev
    Next
    INDEX
    Explanations

    requests for explicit or sexual content and rejects them based on safety guidelines.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    data fragments classification level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    这种
    0.50
    (
    0.42
    ärt
    0.39
    ໃນ
    0.38
     Branson
    0.38
    Proofs
    0.37
    bersome
    0.37
     بهذا
    0.37
    izar
    0.36
    ické
    0.36
    POSITIVE LOGITS
     സമയം
    0.41
     இருவரும்
    0.40
     것처럼
    0.40
    yyati
    0.39
     ゆ
    0.39
    elesaian
    0.39
     ज्यामुळे
    0.39
    ष्य
    0.38
     வாக
    0.38
     🙌
    0.38
    Activations Density 0.320%

    No Known Activations