© 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. 870
    Prev
    Next
    INDEX
    Explanations

    explaining things step by step

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

    the type, or followed by punctuation

    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
     trước
    0.28
     tiếng
    0.26
    缱
    0.26
     chết
    0.26
     поез
    0.26
     незакон
    0.26
     śmier
    0.25
     giá
    0.25
     sạch
    0.25
     cười
    0.25
    POSITIVE LOGITS
     مرکزی
    0.25
     ਉਨ੍ਹਾਂ
    0.25
    ウス
    0.25
     მათ
    0.24
     alluvial
    0.24
    ੜ
    0.24
     পক্ষ
    0.23
     בק
    0.23
     demarc
    0.23
    さまざまな
    0.23
    Activations Density 0.000%

    No Known Activations