© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8716
    Prev
    Next
    INDEX
    Explanations

    business/brand names

    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
     workpiece
    0.50
     coil
    0.46
     granularity
    0.46
    繁忙時間服務
    0.46
    >∈</
    0.45
     ternary
    0.45
     pigmented
    0.45
     isotropic
    0.44
    ្សែ
    0.44
     optimised
    0.43
    POSITIVE LOGITS
    ™
    0.75
     LLC
    0.60
     Ltd
    0.58
     Studios
    0.57
     Promotions
    0.56
    ™,
    0.52
     Corporation
    0.52
    TM
    0.50
     ™
    0.50
     Incorporated
    0.50
    Activations Density 0.009%

    No Known Activations