© 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. 6171
    Prev
    Next
    INDEX
    Explanations

    requests and offers

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

    tokens in assistant messages that offer help or ask the user for more information (requests to share code/details or invitations to continue).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    ۔
    0.29
    。
    0.28
    ،
    0.25
    ，
    0.24
    .
    0.24
    》，
    0.21
    、
    0.21
     (
    0.20
     polynomial
    0.19
     ล
    0.19
    POSITIVE LOGITS
     it
    0.34
     we
    0.30
    you
    0.30
    we
    0.29
    it
    0.27
    They
    0.26
     they
    0.25
     они
    0.25
     அதை
    0.25
     you
    0.25
    Activations Density 0.381%

    No Known Activations