© 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. 10893
    Prev
    Next
    INDEX
    Explanations

    XML declaration and numbers

    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
    ٠
    1.73
    ٥
    1.62
    ٣
    1.58
    𝓽
    1.52
     jumper
    1.44
    ρ
    1.41
    ële
    1.39
    ｉ
    1.36
     bygone
    1.36
    ｏ
    1.35
    POSITIVE LOGITS
    ре
    1.50
    人们
    1.38
    人民
    1.35
    问题
    1.32
    frac
    1.31
    सूर
    1.31
    人
    1.29
    人物
    1.28
    наче
    1.27
    话题
    1.26
    Activations Density 0.000%

    No Known Activations