© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13311
    Prev
    Next
    INDEX
    Explanations

    God, Word, glory

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

    sigmoid function and cross-entropy

    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_16k_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
    ɺ
    0.45
    stö
    0.40
    ровано
    0.40
    toLocale
    0.39
    ToRemove
    0.39
     কক্ষে
    0.39
     পালাতে
    0.38
     возле
    0.38
    wheres
    0.38
    segu
    0.38
    POSITIVE LOGITS
     빛
    0.46
     confided
    0.39
     editorials
    0.38
    editorial
    0.38
     Exemple
    0.38
     الكهربائيه
    0.38
     Azi
    0.38
     lighted
    0.37
     WINDOW
    0.37
     infect
    0.37
    Activations Density 0.065%

    No Known Activations