© 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. 42533
    Prev
    Next
    INDEX
    Explanations

    mix of languages

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

    abbreviations and their explanations

    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
    h
    1.08
    (
    1.05
    de
    1.05
    ли
    1.02
    '
    0.94
    can
    0.90
    ’
    0.88
    nya
    0.87
    ：
    0.87
    of
    0.84
    POSITIVE LOGITS
    0.93
    ្សែ
    0.70
    痿
    0.66
    为人
    0.66
    らは
    0.64
    verständlich
    0.64
    很好的
    0.64
     äh
    0.63
    اسية
    0.63
    的基础
    0.62
    Activations Density 0.116%

    No Known Activations