© 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. 188007
    Prev
    Next
    INDEX
    Explanations

    looking for

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

    EOF while parsing

    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
    veled
    0.50
    <-
    0.47
    这个问题
    0.46
     playtime
    0.45
    <0x99>
    0.44
    Dish
    0.44
    衬
    0.44
    
    0.43
    恐
    0.43
    傻
    0.42
    POSITIVE LOGITS
     Où
    0.55
     ayudar
    0.50
    部門
    0.50
     móvil
    0.48
     Careers
    0.47
     Programa
    0.46
     Pran
    0.46
     Turqu
    0.45
     đạo
    0.45
     mencari
    0.45
    Activations Density 0.001%

    No Known Activations