© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147290
    Prev
    Next
    INDEX
    Explanations

    interconnected nodes or Chinese Room or cooked egg

    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
     Benutzer
    0.72
    형
    0.71
     कोश
    0.68
    enarios
    0.66
     Duis
    0.65
    🪐
    0.65
    ዶች
    0.65
    idor
    0.65
    UserInfo
    0.65
    Repository
    0.65
    POSITIVE LOGITS
     takeaway
    0.68
     cereal
    0.68
    ˒
    0.67
    лизации
    0.64
     ше
    0.64
     प्री
    0.64
     amb
    0.63
     ha
    0.62
     pretreatment
    0.62
     front
    0.61
    Activations Density 0.005%

    No Known Activations