© 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. 136909
    Prev
    Next
    INDEX
    Explanations

    time and additional

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

    financial or legal concepts

    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
    довле
    0.55
     Бу
    0.52
    뚜
    0.52
    сім
    0.49
    ermanfaat
    0.49
     Ру
    0.48
     Зна
    0.48
     ча
    0.48
    сна
    0.48
     функ
    0.47
    POSITIVE LOGITS
     hide
    0.48
    वलं
    0.45
    دانلود
    0.42
     Eulerian
    0.41
     کہنے
    0.40
    -
    0.40
    FERENCE
    0.40
    সল
    0.39
     ouvrir
    0.39
     menghilangkan
    0.39
    Activations Density 0.003%

    No Known Activations