© 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. 159211
    Prev
    Next
    INDEX
    Explanations

    furniture and interior design

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

    exterior gateway

    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
     querido
    0.48
    大家都
    0.47
     bilhões
    0.47
     દરમ
    0.46
    ículos
    0.45
    ostí
    0.45
    pengaruhi
    0.45
    爹
    0.44
     తమి
    0.44
    avin
    0.43
    POSITIVE LOGITS
     woodworking
    0.55
     IKEA
    0.54
     mezzanine
    0.48
     arbe
    0.47
     Ikea
    0.47
     ona
    0.46
     installations
    0.46
     minut
    0.46
     augmented
    0.46
     walnut
    0.46
    Activations Density 0.001%

    No Known Activations