© 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. 73213
    Prev
    Next
    INDEX
    Explanations

    give/gives/gives you

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

    increasing function, immigrant and, distributors provide

    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
     aquellas
    0.46
     eyesight
    0.42
     additionally
    0.41
     झाल्यानंतर
    0.41
     ឬ
    0.40
     axonal
    0.40
     aquellos
    0.39
    巧
    0.39
    지막
    0.39
     Những
    0.39
    POSITIVE LOGITS
    ōu
    0.51
     Tern
    0.48
    rž
    0.47
    èche
    0.45
    oda
    0.44
    ค้า
    0.44
     Вай
    0.43
     SaaS
    0.43
     মশ
    0.43
     फल
    0.43
    Activations Density 0.001%

    No Known Activations