© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10724
    Prev
    Next
    INDEX
    Explanations

    three, তিনটি, three, Three, 、,三个, तीनों

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    constraintlayout
    0.41
    berge
    0.35
    └──
    0.34
     confine
    0.33
    ल्यानंतर
    0.33
    iore
    0.32
    0.32
     CALIFORNIA
    0.32
    和大
    0.32
    clos
    0.31
    POSITIVE LOGITS
    -,
    0.78
    ?,?,
    0.70
    、
    0.69
     three
    0.59
     তিনটি
    0.58
    three
    0.56
    Three
    0.55
     、,
    0.55
    三个
    0.54
     तीनों
    0.54
    Activations Density 0.670%

    No Known Activations