© 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. 147930
    Prev
    Next
    INDEX
    Explanations

    bread, pita, biscuits, baguette

    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
     بينا
    0.76
     رہے
    0.74
     Potato
    0.71
     স্বাক্ষ
    0.70
     krás
    0.68
    erate
    0.68
     reducible
    0.67
    ὄ
    0.67
     Bak
    0.66
    クラ
    0.66
    POSITIVE LOGITS
     drenched
    0.85
     soaked
    0.79
     soaking
    0.78
    Pupp
    0.77
    向量
    0.72
    ؕ
    0.72
     चुनने
    0.71
     smother
    0.70
     accompany
    0.67
     selection
    0.66
    Activations Density 0.014%

    No Known Activations