© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33490
    Prev
    Next
    INDEX
    Explanations

    common words / phrases across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çünkü
    0.54
     perché
    0.51
     क्योंकि
    0.50
    。
    0.49
    But
    0.46
    ።
    0.45
     porque
    0.45
     किंतु
    0.45
    }.
    0.45
     ако
    0.45
    POSITIVE LOGITS
     we
    0.79
     possiamo
    0.73
     فإن
    0.70
     우리는
    0.67
     it
    0.66
     podemos
    0.66
    我们可以
    0.66
     there
    0.65
     udało
    0.62
    我們可以
    0.62
    Activations Density 0.038%

    No Known Activations