© 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. 77148
    Prev
    Next
    INDEX
    Explanations

    buildings, places, abstract concepts

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

    tax reduce

    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
    መሪያ
    0.48
     DBC
    0.46
     NPR
    0.46
     Kyiv
    0.44
    ्योर
    0.44
     NVIC
    0.44
     AVR
    0.43
    ?}
    0.43
    ᆹ
    0.43
     मृ
    0.41
    POSITIVE LOGITS
    建築
    0.48
    WARD
    0.47
    禅
    0.46
    gebäude
    0.46
     cérémon
    0.45
    retanto
    0.45
     giardino
    0.44
     アイス
    0.44
    实验室
    0.43
     تصور
    0.43
    Activations Density 0.001%

    No Known Activations