© 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. 147874
    Prev
    Next
    INDEX
    Explanations

    recipe yields

    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
    topic
    0.66
    互
    0.61
    หล
    0.61
    تق
    0.59
     trasporto
    0.59
     favorably
    0.58
    tip
    0.58
     combining
    0.57
    package
    0.57
    table
    0.57
    POSITIVE LOGITS
     pobreza
    0.78
     obtus
    0.75
    改成
    0.75
     deserts
    0.73
    ultats
    0.73
     اوكي
    0.73
    过于
    0.70
    ⓔ
    0.69
    ancies
    0.69
    ஞ்ச
    0.69
    Activations Density 0.002%

    No Known Activations