© 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. 110728
    Prev
    Next
    INDEX
    Explanations

    search and related

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

    search and prediction

    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
    можно
    0.48
    amese
    0.46
    िष्ट
    0.45
     चौपट
    0.45
     инсу
    0.44
    ös
    0.44
    ívá
    0.43
    ዱ
    0.43
     추진
    0.42
    ollen
    0.42
    POSITIVE LOGITS
     javac
    0.47
     поиска
    0.46
     recherche
    0.45
     busca
    0.44
     search
    0.44
     SEARCH
    0.44
    পূর্ন
    0.43
     Yaj
    0.42
     вывод
    0.41
     প্রশ্নে
    0.41
    Activations Density 0.000%

    No Known Activations