© 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. 42492
    Prev
    Next
    INDEX
    Explanations

    exploring woodworking and sending

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

    foreign and numerical quantities

    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
    лото
    0.51
     рестора
    0.48
    น
    0.48
    Pedido
    0.47
    或者
    0.47
     בס
    0.47
    歟
    0.46
    𝗔
    0.46
    尤其
    0.45
    도
    0.45
    POSITIVE LOGITS
     zwei
    0.58
     fünf
    0.57
     eine
    0.57
     který
    0.57
     viaj
    0.53
    ronaut
    0.52
     einer
    0.52
     cuatro
    0.52
     redesigned
    0.52
    it
    0.51
    Activations Density 0.000%

    No Known Activations