© 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. 10998
    Prev
    Next
    INDEX
    Explanations

    names with "amma" or "a" endings

    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
    𝐢
    1.72
    榄
    1.64
    nas
    1.57
    𝐫
    1.52
     sty
    1.49
    েন্ট
    1.49
    ことができます
    1.45
     ற
    1.44
    𝐞
    1.44
     produc
    1.39
    POSITIVE LOGITS
    儡
    1.59
     Interestingly
    1.58
     العلوم
    1.54
    莹
    1.52
    ೈನ
    1.46
    เอง
    1.45
     مشینوں
    1.44
    Interestingly
    1.42
    ্বিক
    1.42
     benefited
    1.42
    Activations Density 0.000%

    No Known Activations