© 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. 22-GEMMASCOPE-2-RES-65K
    7. 8115
    Prev
    Next
    INDEX
    Explanations

    paper

    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_22_width_65k_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
    珐
    0.86
    قول
    0.85
     pots
    0.78
    ジュエリー
    0.78
    甕
    0.77
    Ruby
    0.75
    athar
    0.75
    硬件
    0.72
    Concrete
    0.72
    鑲
    0.70
    POSITIVE LOGITS
     paper
    2.49
     Paper
    2.18
     kertas
    2.05
    paper
    2.01
    Paper
    1.99
    纸
    1.97
     papers
    1.91
     PAPER
    1.90
     бумаги
    1.87
    紙
    1.83
    Activations Density 0.231%

    No Known Activations