© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55339
    Prev
    Next
    INDEX
    Explanations

    sophisticated network logistics

    np_acts-logits-general · gemini-2.5-flash-lite

    higher mileage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وين
    0.60
    典
    0.52
    有一天
    0.51
     Bél
    0.51
    likes
    0.50
    卸
    0.50
    到了
    0.50
    آن
    0.49
    學者
    0.49
    愪
    0.48
    POSITIVE LOGITS
     lo
    0.51
     looping
    0.50
    ‌پ
    0.48
     ciclo
    0.48
     gi
    0.48
     tồn
    0.46
     used
    0.46
     pinched
    0.46
     printed
    0.46
     sucked
    0.45
    Activations Density 0.002%

    No Known Activations