© 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. 239109
    Prev
    Next
    INDEX
    Explanations

    published offer

    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
     eurozone
    0.54
     евро
    0.53
     यूरोपीय
    0.53
     europé
    0.53
    <unused68>
    0.52
     pembelian
    0.52
    рия
    0.52
     kimchi
    0.51
     beverage
    0.51
     zucchini
    0.50
    POSITIVE LOGITS
    iore
    0.50
     Dorsey
    0.50
    道
    0.48
    on
    0.46
    printk
    0.46
    个数
    0.45
    trails
    0.45
    개가
    0.45
    或
    0.45
    sudo
    0.44
    Activations Density 0.000%

    No Known Activations