© 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. 198205
    Prev
    Next
    INDEX
    Explanations

    that is to say, meaning

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

    special characters and delimiters

    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
     ‬
    0.48
    ـ
    0.46
     ؟
    0.44
     commendable
    0.43
     ۔
    0.43
    きましたが
    0.42
    تر
    0.42
    atherapy
    0.42
     ؛
    0.41
    آ
    0.41
    POSITIVE LOGITS
    也就是说
    0.82
    比如说
    0.56
     यानी
    0.54
    也就是
    0.54
     म्हणजेच
    0.53
     тобто
    0.52
    这个
    0.52
     这个
    0.52
     이걸
    0.51
    比如說
    0.50
    Activations Density 0.018%

    No Known Activations