© 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. 10393
    Prev
    Next
    INDEX
    Explanations

    user query

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

    phrases and tokens indicating a user request or question (polite/requesting intent such as "what," "tell me," "could you," "please," and "thank you").

    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
     streetwear
    0.79
     unsurprisingly
    0.74
     badass
    0.72
    🔥
    0.72
     💪
    0.64
     reimag
    0.64
    Haha
    0.64
     lmao
    0.64
     shenanigans
    0.63
     🔥
    0.63
    POSITIVE LOGITS
     изпол
    0.70
     Presently
    0.60
    ホームページ
    0.60
     numai
    0.60
     Mgr
    0.60
    笫
    0.60
     Assn
    0.59
     microfilm
    0.59
     .
    0.59
     granddaughter
    0.58
    Activations Density 0.041%

    No Known Activations