© 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. 236477
    Prev
    Next
    INDEX
    Explanations

    rates, rentals, attractions, sores, trademarks

    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
    ya
    0.46
    lijke
    0.45
    sterreich
    0.43
    vanje
    0.43
     Abbas
    0.42
    黑色
    0.41
    jez
    0.40
    消
    0.40
    buru
    0.40
    lista
    0.40
    POSITIVE LOGITS
     newborns
    0.55
     экстре
    0.52
     tokamaks
    0.51
     Timelapse
    0.50
     ulcers
    0.49
     phổi
    0.49
     lâng
    0.49
     cathodes
    0.49
     больных
    0.49
     кру
    0.48
    Activations Density 0.000%

    No Known Activations