© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222429
    Prev
    Next
    INDEX
    Explanations

    inquiry and knowledge seeking

    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_40_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
     menciona
    0.40
     isti
    0.40
     răng
    0.38
     deduct
    0.37
     Surv
    0.37
     தா
    0.36
    Ꮽ
    0.36
    yai
    0.36
    Tanh
    0.35
    ϵ
    0.35
    POSITIVE LOGITS
     enquiry
    0.56
     enquiries
    0.55
     Enquiry
    0.51
     enqu
    0.47
     inquiries
    0.47
    knowledge
    0.46
     Knowledge
    0.46
     inquiring
    0.46
    Knowledge
    0.45
     Questions
    0.43
    Activations Density 0.002%

    No Known Activations