© 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. 15279
    Prev
    Next
    INDEX
    Explanations

    found within

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

    location or existence

    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
     этим
    0.55
     svojim
    0.54
     în
    0.52
     در
    0.51
    在我们
    0.49
    ในการ
    0.49
    在我
    0.48
     katika
    0.47
     swoim
    0.47
     जब
    0.46
    POSITIVE LOGITS
     terdapat
    0.69
     शामिल
    0.68
     നിന്ന്
    0.61
     सामील
    0.59
    が含ま
    0.58
    erdapat
    0.57
     ውስጥ
    0.57
     يوجد
    0.57
    നിന്ന്
    0.57
    含ま
    0.54
    Activations Density 0.082%

    No Known Activations