© 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. 243703
    Prev
    Next
    INDEX
    Explanations

    member mills

    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
     でしょう
    0.55
     comunità
    0.54
    Rental
    0.52
     definisi
    0.52
     rispett
    0.51
     conhece
    0.50
     您
    0.49
    ᱠ
    0.49
     berdiri
    0.49
     guaranteed
    0.48
    POSITIVE LOGITS
    getMetering
    0.49
     Americans
    0.43
     unnatural
    0.43
    iyim
    0.43
     outcry
    0.43
    एक्स
    0.42
    iav
    0.42
     EUA
    0.41
    有个
    0.41
     Ew
    0.41
    Activations Density 0.001%

    No Known Activations