© 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. 195453
    Prev
    Next
    INDEX
    Explanations

    punctuation and foreign words

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

    language and explanations

    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
    entemente
    0.48
     ખાસ
    0.47
    ม
    0.46
     непосред
    0.45
    öss
    0.44
     тепло
    0.43
     национа
    0.43
     нагре
    0.43
     Besonders
    0.43
     Особенно
    0.43
    POSITIVE LOGITS
    至今
    0.54
    ﺖ
    0.51
     Juin
    0.50
    ISTAN
    0.49
    趣
    0.48
    LOLL
    0.46
     benefactor
    0.46
     più
    0.46
    lebih
    0.46
    лением
    0.45
    Activations Density 0.001%

    No Known Activations