© 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. 10908
    Prev
    Next
    INDEX
    Explanations

    code and dataframes

    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
    Вот
    1.48
     alley
    1.41
    ियों
    1.40
     Вот
    1.40
    اً
    1.37
     obwohl
    1.36
    ordinaire
    1.36
    uary
    1.36
     inan
    1.33
    ously
    1.31
    POSITIVE LOGITS
    ed
    3.26
    ת
    2.74
    ل
    2.65
    ة
    2.46
    이
    2.41
    ing
    2.34
    ت
    2.31
    了
    2.30
    на
    2.14
    ה
    2.12
    Activations Density 0.076%

    No Known Activations