© 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. 10992
    Prev
    Next
    INDEX
    Explanations

    would give

    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
    ح
    1.55
    Không
    1.38
    𝘣
    1.36
    colare
    1.35
    ط
    1.33
    ف
    1.33
     lemons
    1.33
     amb
    1.32
    ها
    1.28
    Ớ
    1.25
    POSITIVE LOGITS
    йл
    1.23
    英語版
    1.09
    ़
    1.04
    啍
    1.00
    ων
    1.00
    ëren
    0.99
    を起こ
    0.99
    ዎ
    0.98
    ्रेसेस
    0.97
    ܝ
    0.97
    Activations Density 0.000%

    No Known Activations