© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11166
    Prev
    Next
    INDEX
    Explanations

    listening on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    er
    2.00
    or
    1.80
    ликт
    1.73
    ي
    1.71
    र
    1.71
    ли
    1.69
    ма
    1.69
    ी
    1.67
    يّ
    1.64
    ल
    1.63
    POSITIVE LOGITS
     Nxf
    1.64
     पुरालेखित
    1.57
     anhydrous
    1.53
    #__
    1.50
    @"
    1.49
    ﾜ
    1.49
    securitycenter
    1.43
     Epidemiology
    1.41
     arou
    1.41
    1.41
    Activations Density 0.009%

    No Known Activations