© 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. 131181
    Prev
    Next
    INDEX
    Explanations

    statistics and collections

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

    everything or nothing

    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
     Почему
    0.58
     Guillaume
    0.50
     сестра
    0.49
     превы
    0.48
     乗
    0.48
     Я
    0.47
     相
    0.46
     Вы
    0.46
     Что
    0.46
     Поскольку
    0.46
    POSITIVE LOGITS
     rufis
    0.55
    小小
    0.43
    yoruz
    0.43
    桃
    0.43
     فہرست
    0.42
    پاکستان
    0.41
    ₦
    0.41
     COURSE
    0.41
    irán
    0.41
     ativo
    0.41
    Activations Density 0.000%

    No Known Activations