© 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. 253074
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     tuyến
    0.59
    𝘀
    0.57
     huyết
    0.55
     YORK
    0.55
     CMO
    0.55
     наук
    0.54
    𝘴
    0.54
    𝘨
    0.54
    𝗴
    0.53
    ত্বের
    0.52
    POSITIVE LOGITS
     bill
    1.09
     bills
    0.99
    Bills
    0.98
    bill
    0.97
    bills
    0.92
     Bill
    0.83
    Bill
    0.82
     Bills
    0.81
    BILL
    0.70
    ビリ
    0.68
    Activations Density 0.075%

    No Known Activations