© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12134
    Prev
    Next
    INDEX
    Explanations

    WHERE clause filtering or Configuration settings

    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
    ոտ
    0.41
    얏
    0.39
     debug
    0.38
     अज
    0.38
     release
    0.38
     QA
    0.37
     sheath
    0.36
     совмести
    0.36
     RELEASE
    0.36
    ျ
    0.36
    POSITIVE LOGITS
     Configuration
    0.59
    Configuration
    0.58
    configuration
    0.52
     configuration
    0.48
    abs
    0.47
    '
    0.46
    കേന്ദ്രം
    0.43
    MSBuildTools
    0.43
    DefineConstants
    0.42
    GLOBALS
    0.42
    Activations Density 0.000%

    No Known Activations