© 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. 228644
    Prev
    Next
    INDEX
    Explanations

    company or people leading

    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
     দেখেন
    0.49
    农业
    0.49
    ujeme
    0.48
    legte
    0.48
     ഭൂ
    0.46
    䀠
    0.46
    iav
    0.46
     образа
    0.46
     शू
    0.46
    끌
    0.45
    POSITIVE LOGITS
    رے
    0.51
     summation
    0.49
     hectic
    0.46
     compositional
    0.46
     perimeter
    0.44
     weaponry
    0.43
    [,
    0.43
     moieties
    0.43
     ictal
    0.43
     tapered
    0.42
    Activations Density 0.000%

    No Known Activations