© 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. 2707
    Prev
    Next
    INDEX
    Explanations

    description or definition context

    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
     whiche
    0.26
     ซึ่ง
    0.25
    繁忙時間服務
    0.25
     型
    0.25
     typename
    0.24
    ឹម
    0.23
    OGRAPHY
    0.23
    ائص
    0.22
    。
    0.22
    装着
    0.22
    POSITIVE LOGITS
     Requires
    0.34
     gets
    0.33
     Allows
    0.33
     Provides
    0.32
     требует
    0.31
     doesn
    0.30
     gives
    0.30
     provides
    0.30
     has
    0.29
     requires
    0.29
    Activations Density 0.063%

    No Known Activations