© 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. 146002
    Prev
    Next
    INDEX
    Explanations

    tikz plots

    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
     কোন্‌
    0.69
     мальчика
    0.68
    迳
    0.66
     alvo
    0.66
    逑
    0.65
     অবশিষ্ট
    0.65
     lleva
    0.65
     oznacza
    0.65
     Cont
    0.65
    刳
    0.64
    POSITIVE LOGITS
    arre
    0.78
    tran
    0.74
     ép
    0.70
     erkannt
    0.69
     glycer
    0.68
    sheets
    0.67
     fairs
    0.66
    graphs
    0.65
     علی
    0.65
    触
    0.65
    Activations Density 0.004%

    No Known Activations