© 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. 245140
    Prev
    Next
    INDEX
    Explanations

    most beneficial adjectives

    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
     contando
    0.44
    мур
    0.44
    <0xA8>
    0.42
    пуль
    0.42
    agment
    0.42
    óny
    0.41
     fatta
    0.41
     коктей
    0.41
    <0xA1>
    0.41
    MASS
    0.40
    POSITIVE LOGITS
     iris
    0.54
     Dris
    0.52
    啓
    0.51
     En
    0.51
     Elim
    0.48
     ប៉ុ
    0.48
     Prel
    0.48
     प्री
    0.47
     عملی
    0.47
    ตา
    0.47
    Activations Density 0.001%

    No Known Activations