© 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-16K
    7. 2519
    Prev
    Next
    INDEX
    Explanations

    business, finance, law, stock, product

    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_16k_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
    ‡
    0.76
     Så
    0.72
     स्थानिक
    0.71
    古代
    0.70
    Så
    0.70
    डॉ
    0.69
    以
    0.68
    lok
    0.67
    重要的
    0.65
     以
    0.64
    POSITIVE LOGITS
    体系
    0.81
     civilization
    0.81
     realm
    0.80
     wharf
    0.79
     subsidy
    0.77
     Festival
    0.77
     dormitory
    0.77
     veines
    0.75
     halls
    0.75
    圈
    0.74
    Activations Density 0.109%

    No Known Activations