© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9268
    Prev
    Next
    INDEX
    Explanations

    stock, address, customer, terms, closed

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

    free,

    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_40_width_16k_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
    நான்
    0.43
    Я
    0.42
    메라
    0.39
     subalgebras
    0.39
     Higgs
    0.38
    하
    0.38
    ());
    0.37
    Фу
    0.37
    Й
    0.37
    வுக
    0.36
    POSITIVE LOGITS
    arup
    0.42
     然而
    0.41
     நிகழ்
    0.40
     ooit
    0.40
    landet
    0.39
     azonban
    0.38
     नेक्स्ट
    0.38
     कंडी
    0.37
     చరిత్ర
    0.37
    Kah
    0.37
    Activations Density 0.219%

    No Known Activations