© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9909
    Prev
    Next
    INDEX
    Explanations

    difference and comparison

    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
    ″
    3.14
    ید
    2.91
    การณ์
    2.68
     aikana
    2.58
    \!\
    2.57
    ᐟ
    2.56
    +",
    2.51
    čných
    2.47
     ulter
    2.47
    بة
    2.47
    POSITIVE LOGITS
    a
    4.55
    ה
    4.50
    ați
    3.66
    ા
    3.18
    리카
    2.99
    ா
    2.98
    া
    2.95
    רץ
    2.92
    aun
    2.83
    ликт
    2.78
    Activations Density 0.128%

    No Known Activations