© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 128484
    Prev
    Next
    INDEX
    Explanations

    sounds like tiny

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

    health and physical conditions

    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
    上也
    0.42
    全
    0.42
    的全
    0.39
    ־
    0.39
    倦
    0.38
    RQ
    0.38
    展
    0.38
    SAP
    0.38
    之
    0.38
    的其他
    0.38
    POSITIVE LOGITS
     programa
    0.55
     shampoos
    0.50
     hiszen
    0.50
     प्रच
    0.49
     maquillaje
    0.49
     trứng
    0.49
     produktów
    0.49
     çizg
    0.49
     Egipto
    0.49
     પેટ્રોલ
    0.49
    Activations Density 0.000%

    No Known Activations