© 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. 20274
    Prev
    Next
    INDEX
    Explanations

    knowing what

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

    Leonardo da Vinci

    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
    grade
    0.54
     (+)
    0.51
     satu
    0.50
    裡
    0.48
    hrad
    0.46
     presente
    0.46
     Technologies
    0.45
     piso
    0.45
    ada
    0.45
     sé
    0.45
    POSITIVE LOGITS
    LookAndFeel
    0.52
    ار
    0.49
    myLabels
    0.48
    AspNet
    0.48
    Macros
    0.47
    Flair
    0.47
    Cutting
    0.45
     ቅር
    0.45
    ய
    0.45
    ل
    0.44
    Activations Density 0.000%

    No Known Activations