© 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. 163457
    Prev
    Next
    INDEX
    Explanations

    FODMAP, functions, data, seller

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

    | COVID-19 pandemic, anomalies, networks

    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
    راف
    0.48
    )->
    0.47
    leftarrow
    0.46
    )++;
    0.46
    少了
    0.46
    Customers
    0.45
    ちょ
    0.45
    C
    0.45
    しまう
    0.45
    برو
    0.44
    POSITIVE LOGITS
     ຂ
    0.57
     día
    0.51
     দিনের
    0.50
     day
    0.49
     돌아
    0.49
     य
    0.49
     अधिकांश
    0.49
     ذكر
    0.47
     보는
    0.47
     holiness
    0.47
    Activations Density 0.000%

    No Known Activations