© 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. 41-GEMMASCOPE-2-RES-262K
    7. 61400
    Prev
    Next
    INDEX
    Explanations

    finding or searching information

    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_all/layer_41_width_262k_l0_big
    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
     ids
    0.47
     வேறு
    0.43
    (`#
    0.43
    ἂ
    0.40
    ាន់
    0.40
     හැකි
    0.39
     코드
    0.38
     ব্যবহার
    0.38
    乱
    0.38
    oxal
    0.37
    POSITIVE LOGITS
     search
    0.80
     searching
    0.76
     searched
    0.74
     Search
    0.71
     Searching
    0.70
     searches
    0.70
    搜尋
    0.70
     SEARCH
    0.67
     querying
    0.65
    查找
    0.64
    Activations Density 0.001%

    No Known Activations