© 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. 197321
    Prev
    Next
    INDEX
    Explanations

    white leather, Play-Doh, Wi-Fi network

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

    goals, businesses, professionals

    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
    த்துவம்
    0.63
    ت
    0.54
    每一个
    0.52
    z
    0.50
    ro
    0.49
    т
    0.49
    ड
    0.49
    ות
    0.49
    tcpHeader
    0.49
    float
    0.49
    POSITIVE LOGITS
     antimony
    0.45
     melan
    0.43
     wallpaper
    0.43
     indium
    0.43
     iodine
    0.43
    ophenyl
    0.41
     appointees
    0.41
     chromatin
    0.40
     extermin
    0.40
     acuity
    0.40
    Activations Density 0.001%

    No Known Activations