© 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. 11770
    Prev
    Next
    INDEX
    Explanations

    assets under management or separation of powers

    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
     deformable
    1.45
    syringe
    1.41
     medallist
    1.39
    annabin
    1.39
    ҽ
    1.37
     Bakufu
    1.34
     userService
    1.33
    できるように
    1.33
    windowFixedWidth
    1.32
     Lloyds
    1.31
    POSITIVE LOGITS
    ed
    1.43
    ة
    1.43
    й
    1.33
    y
    1.21
    ява
    1.16
    macht
    1.15
    า
    1.15
    लिस
    1.14
     الحاس
    1.11
     mankind
    1.09
    Activations Density 0.000%

    No Known Activations