© 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. 28660
    Prev
    Next
    INDEX
    Explanations

    any kind

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

    any kind

    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
     Reprint
    0.44
    Автор
    0.42
    输出
    0.40
     неот
    0.40
    ocial
    0.39
    mpi
    0.37
    Б
    0.37
    З
    0.37
    ieb
    0.36
    nx
    0.36
    POSITIVE LOGITS
    那边
    0.44
     måde
    0.42
    结局
    0.41
    conditionals
    0.40
    таў
    0.40
     প্রান্তে
    0.39
     condiments
    0.39
     condensate
    0.39
     рода
    0.39
     महल
    0.39
    Activations Density 0.000%

    No Known Activations