© 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. 105909
    Prev
    Next
    INDEX
    Explanations

    international words and covid

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

    window function

    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
     Su
    0.48
    苏联
    0.46
     苏
    0.45
    سو
    0.44
     exclusive
    0.43
     Kano
    0.43
     Linux
    0.42
     only
    0.42
     فقط
    0.42
     Kecamatan
    0.41
    POSITIVE LOGITS
     и
    0.54
     миро
    0.49
    covid
    0.49
     και
    0.46
    令和
    0.44
    Covid
    0.44
    चिंत
    0.43
    कोरोना
    0.43
     многочис
    0.43
    和社会
    0.43
    Activations Density 0.000%

    No Known Activations