© 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-262K
    7. 10394
    Prev
    Next
    INDEX
    Explanations

    refusing inappropriate requests due to safety

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

    explanatory follow-up sentences that refer back to the previous idea with a demonstrative lead-in (e.g., “This …”) to clarify, emphasize, or summarize it.

    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
    ]]);
    0.38
    لبية
    0.38
    ندر
    0.37
    قطه
    0.37
     blevet
    0.36
     更新
    0.36
    ފ
    0.34
    更新
    0.34
     তবুও
    0.34
    YPE
    0.34
    POSITIVE LOGITS
    为此
    0.75
    そのため
    0.67
     त्यासाठी
    0.65
     Dafür
    0.63
     requires
    0.57
    requires
    0.57
     therefore
    0.56
    therefore
    0.55
     deshalb
    0.55
     Requires
    0.55
    Activations Density 0.292%

    No Known Activations