© 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. 194667
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    scale, meter, and rating

    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
     我們
    0.66
    t
    0.61
    EN
    0.57
     我们
    0.56
    tr
    0.54
    nl
    0.52
     実
    0.51
     根据
    0.51
    side
    0.50
    ti
    0.50
    POSITIVE LOGITS
    हूर
    0.54
     मिले
    0.52
    साठी
    0.48
     আসছেন
    0.45
    ంటున్నారు
    0.44
    arası
    0.44
     देणे
    0.44
    はお
    0.43
     налази
    0.43
     తిన
    0.42
    Activations Density 0.001%

    No Known Activations