© 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. 152345
    Prev
    Next
    INDEX
    Explanations

    medical and health terms

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

    explaining research methods

    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
     улы
    0.56
    䣷
    0.54
    |।
    0.52
    सि
    0.50
     đãi
    0.50
     карь
    0.48
    udah
    0.48
    ILayout
    0.47
     लोक
    0.46
    ként
    0.46
    POSITIVE LOGITS
    ´
    0.47
    eding
    0.47
     de
    0.46
     M
    0.45
     Regione
    0.44
     stepping
    0.44
    近期
    0.43
     aug
    0.43
     ds
    0.42
    一开始
    0.42
    Activations Density 0.001%

    No Known Activations