© 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. 1392
    Prev
    Next
    INDEX
    Explanations

    Kitchen Island

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

    numbered lists

    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
     veřej
    0.45
    别墅
    0.44
    Gosudarstvennyj
    0.43
    禳
    0.42
    ेंसिल
    0.41
     مواد
    0.41
    연구
    0.40
     prévoit
    0.40
     katalog
    0.40
     تقوم
    0.40
    POSITIVE LOGITS
     other
    0.50
    s
    0.49
     \
    0.47
    m
    0.46
     {
    0.44
     =
    0.42
     &
    0.40
    C
    0.40
    ↵
    0.39
     and
    0.39
    Activations Density 0.037%

    No Known Activations