© 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. 193915
    Prev
    Next
    INDEX
    Explanations

    harm associated with terms

    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
    $^{-
    0.46
    ibfk
    0.38
    SPEC
    0.37
     PROC
    0.37
    ឧបករណ៍
    0.36
    计算机
    0.36
     రాజ్య
    0.36
    叓
    0.36
    প্র
    0.35
     Schönheit
    0.35
    POSITIVE LOGITS
    aver
    0.44
     subtle
    0.39
    sorption
    0.39
     Aff
    0.38
     संप
    0.38
     official
    0.37
    elementType
    0.37
     plus
    0.36
    登
    0.36
    lv
    0.35
    Activations Density 0.000%

    No Known Activations