© 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. 154227
    Prev
    Next
    INDEX
    Explanations

    specific examples or descriptions

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

    Fujian province

    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
     প্রশস্ত
    0.45
     ~
    0.42
    ,$
    0.42
     သ
    0.41
     ~,
    0.41
     包括
    0.41
     (($
    0.39
     (,
    0.39
    ,|\
    0.39
    šli
    0.38
    POSITIVE LOGITS
    Idioma
    0.51
    elemento
    0.46
    Elementos
    0.46
    Sul
    0.46
    пти
    0.45
    ਹਾ
    0.45
     pastry
    0.44
     liquides
    0.44
    blind
    0.43
     времен
    0.42
    Activations Density 0.006%

    No Known Activations