© 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. 254709
    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
     anunció
    0.47
    원이
    0.46
    에도
    0.46
    льний
    0.46
     ጎ
    0.45
    ítulos
    0.44
    IServerGame
    0.44
    َات
    0.43
    다른
    0.43
    원은
    0.43
    POSITIVE LOGITS
     xuân
    0.48
    ེ
    0.46
     Lesbian
    0.43
    ih
    0.43
     me
    0.42
     Gender
    0.41
    Gender
    0.41
    <0x93>
    0.40
     CALLBACK
    0.40
     Жен
    0.40
    Activations Density 0.000%

    No Known Activations