© 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. 253670
    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
    templates
    0.51
    提醒
    0.49
    ম্পতি
    0.47
    ্রেক
    0.46
    SIMPLE
    0.45
    शिता
    0.44
    容
    0.44
    黴
    0.44
    简单的
    0.43
    дили
    0.43
    POSITIVE LOGITS
    /
    0.55
    /(
    0.51
     یا
    0.49
     अथवा
    0.46
     Rup
    0.45
    yah
    0.44
     Secretariat
    0.44
     या
    0.43
     Emer
    0.43
     Orion
    0.43
    Activations Density 0.001%

    No Known Activations