© 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. 158921
    Prev
    Next
    INDEX
    Explanations

    time and place

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

    leaning back slightly

    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
     виду
    0.48
     붙
    0.47
     आउट
    0.46
    Vu
    0.45
     loài
    0.45
    덩
    0.44
    iji
    0.43
     mình
    0.43
     सालों
    0.43
    Mình
    0.42
    POSITIVE LOGITS
    s
    0.54
     unexplained
    0.50
     investigative
    0.46
     Wex
    0.46
    alabel
    0.46
     missed
    0.46
    mise
    0.46
    مسه
    0.45
     radiated
    0.45
    i
    0.45
    Activations Density 0.001%

    No Known Activations