© 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. 86668
    Prev
    Next
    INDEX
    Explanations

    room size and fitting

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

    storage requirements

    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
    tiden
    0.39
     cass
    0.39
     hitam
    0.38
    ᱛ
    0.38
    ницу
    0.38
     vidrio
    0.38
     retails
    0.38
    ⚋
    0.38
    тин
    0.38
     Dop
    0.38
    POSITIVE LOGITS
     공간
    0.75
     пространства
    0.70
     space
    0.65
    空間
    0.64
    空间
    0.63
     cramped
    0.63
    的空间
    0.62
     espacio
    0.61
     فضای
    0.61
     crowding
    0.60
    Activations Density 0.158%

    No Known Activations