© 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. 104162
    Prev
    Next
    INDEX
    Explanations

    path, many, Russian, end

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

    definition and explanation of terms

    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
     coni
    0.51
     Asi
    0.50
     Nikola
    0.49
     Nizam
    0.48
     وګټ
    0.48
     ç
    0.47
    ä
    0.47
     Jazeera
    0.47
     memperoleh
    0.47
     congratulate
    0.46
    POSITIVE LOGITS
    Коммента
    0.55
    等等
    0.49
    很多
    0.47
    改进
    0.47
    Variance
    0.47
    ETER
    0.46
    하지만
    0.46
    VIDENCE
    0.46
    클
    0.46
    其他
    0.46
    Activations Density 0.001%

    No Known Activations