© 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. 233620
    Prev
    Next
    INDEX
    Explanations

    categorization

    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
    撥
    0.43
    生産
    0.42
     Aya
    0.40
    計測
    0.40
    ಲೆ
    0.39
    ارق
    0.39
    stagram
    0.39
     ");
    0.38
    דם
    0.38
    greencar
    0.38
    POSITIVE LOGITS
     reeds
    0.52
     kategor
    0.51
     categorization
    0.51
     categorie
    0.49
     катего
    0.48
     kategorii
    0.47
     category
    0.46
    分类
    0.45
    categor
    0.44
     classific
    0.44
    Activations Density 0.003%

    No Known Activations