© 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. 165607
    Prev
    Next
    INDEX
    Explanations

    Ngorongoro

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

    specific terminology and concepts

    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
    貝
    0.42
     方
    0.41
    ครั้ง
    0.41
     利用
    0.40
    %\
    0.39
     دف
    0.38
    mortem
    0.38
    \"\
    0.38
    де
    0.38
    弧
    0.38
    POSITIVE LOGITS
    DirPath
    0.52
     chooser
    0.49
     apakah
    0.48
     anúncios
    0.48
     creations
    0.47
    ۹
    0.47
     ذاتی
    0.46
     creación
    0.46
     creada
    0.44
    కీయ
    0.44
    Activations Density 0.000%

    No Known Activations