© 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. 10722
    Prev
    Next
    INDEX
    Explanations

    enough data or to see

    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
    こと
    1.42
    <0xE7>
    1.14
    ClrType
    1.09
    auté
    1.08
    पीएससी
    1.07
    verständlich
    1.05
     wording
    1.05
    buildCommand
    1.05
     liable
    1.04
    lingu
    1.00
    POSITIVE LOGITS
    וא
    1.41
    $),
    1.36
    )=$
    1.35
    n
    1.35
    
    1.33
     Nella
    1.30
    ০০০
    1.30
    ট
    1.29
    ლო
    1.29
     disposizione
    1.28
    Activations Density 0.000%

    No Known Activations