© 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. 99195
    Prev
    Next
    INDEX
    Explanations

    real estate listings and parables

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

    Japanese eel, mortality, modern, menopause

    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
     страницы
    0.55
     страница
    0.52
     الهول
    0.49
     ۳
    0.48
     الثانية
    0.46
     откры
    0.46
     применя
    0.45
     править
    0.45
     الشمال
    0.45
     хозя
    0.44
    POSITIVE LOGITS
     silam
    0.47
    it
    0.46
    нага
    0.44
    訃
    0.44
    ウ
    0.43
    ᅳ
    0.42
    ographies
    0.42
    肢
    0.42
     sac
    0.41
     quelconque
    0.41
    Activations Density 0.001%

    No Known Activations