© 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. 53199
    Prev
    Next
    INDEX
    Explanations

    image into

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

    content structure

    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
     rezat
    0.46
     fur
    0.46
     sumber
    0.45
    ㄽ
    0.44
    newValue
    0.44
    导致的
    0.43
    സ്‌
    0.42
     gsap
    0.42
    ښت
    0.42
     ピンク
    0.42
    POSITIVE LOGITS
    ıyoruz
    0.45
    regelen
    0.42
    Chim
    0.41
     мүм
    0.40
     وقف
    0.40
    펴
    0.40
     हंस
    0.39
    Sequential
    0.38
    ဣ
    0.38
    Regulation
    0.38
    Activations Density 0.000%

    No Known Activations