© 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. 55724
    Prev
    Next
    INDEX
    Explanations

    It worked. Every

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

    universally accepted

    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
    Inicio
    0.43
    ývá
    0.39
    виль
    0.38
     ENTRE
    0.38
    ٠
    0.38
    Page
    0.38
     Л
    0.38
     Фи
    0.37
    更多
    0.37
    ى
    0.36
    POSITIVE LOGITS
     drivetrain
    0.54
    četně
    0.52
    電源
    0.51
    電池
    0.50
     elektr
    0.49
     متنوع
    0.49
     elektrische
    0.48
    実装
    0.48
     lekker
    0.47
     دستگاه
    0.47
    Activations Density 0.000%

    No Known Activations