© 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. 29-GEMMASCOPE-2-RES-262K
    7. 146021
    Prev
    Next
    INDEX
    Explanations

    site wise

    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_29_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
     半
    0.71
    قاب
    0.69
     अन्याय
    0.69
    펨
    0.68
    Fluid
    0.68
    ৈতিক
    0.65
    แก้
    0.64
     NodeType
    0.63
    ടുത്ത
    0.63
    Cute
    0.63
    POSITIVE LOGITS
    жээ
    0.73
    ወዳ
    0.68
    Aaj
    0.67
     Ау
    0.62
     brush
    0.62
     soud
    0.60
    ړي
    0.60
    Rose
    0.60
    笔
    0.59
     اسے
    0.58
    Activations Density 0.002%

    No Known Activations