© 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. 6730
    Prev
    Next
    INDEX
    Explanations

    question about safety

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

    Tokens from the user's questions — it activates strongly on words in user-turn queries (the user's utterance/content).

    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
     entsprechenden
    0.31
    規範
    0.31
    احث
    0.30
     peering
    0.29
    Heap
    0.29
    دا
    0.29
     препарата
    0.29
    ман
    0.28
    Formatted
    0.28
    גר
    0.28
    POSITIVE LOGITS
    iktok
    0.42
     boyfriend
    0.41
    赚钱
    0.39
     wikiHow
    0.39
     зимой
    0.39
     billionaires
    0.39
    ？
    0.39
     insanely
    0.38
     फायदेमंद
    0.38
     गर्लफ्रेंड
    0.38
    Activations Density 0.084%

    No Known Activations