© 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. 7697
    Prev
    Next
    INDEX
    Explanations

    surname beginnings

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

    Japanese names and words

    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
    球
    0.23
    zeuge
    0.23
    เค
    0.23
    官网
    0.23
    ruppen
    0.23
    punten
    0.23
    鈉
    0.23
    ImgBoard
    0.23
    在北京
    0.23
     کشور
    0.23
    POSITIVE LOGITS
     desire
    0.21
     aggravate
    0.21
    it
    0.21
     spatially
    0.19
     mural
    0.18
    ak
    0.18
     vadanti
    0.18
     $($
    0.18
     azure
    0.18
     desires
    0.18
    Activations Density 0.080%

    No Known Activations