© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13901
    Prev
    Next
    INDEX
    Explanations

    sports fan

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

    Julia language for math

    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_16k_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
    號
    0.43
     Casino
    0.42
     रोड
    0.38
     電話
    0.38
     pogled
    0.38
    圖
    0.38
    verw
    0.37
    imbang
    0.37
     Lemon
    0.36
    niger
    0.36
    POSITIVE LOGITS
     Julia
    0.66
    Julia
    0.63
    julia
    0.50
    ([(
    0.45
     roca
    0.44
     immunotherapy
    0.44
    !()
    0.42
    (;
    0.42
     endemic
    0.41
    Tables
    0.41
    Activations Density 0.011%

    No Known Activations