© 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. 254869
    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
     modeller
    0.48
     sce
    0.46
     fian
    0.46
    友
    0.46
     cookie
    0.45
    own
    0.45
    لای
    0.44
    icem
    0.44
     project
    0.43
    are
    0.41
    POSITIVE LOGITS
     オール
    0.55
     प्रिज्म
    0.54
     antiguas
    0.54
     स्टोक्स
    0.53
     बहादुर
    0.52
     अधिवेशन
    0.52
    ʢ
    0.52
     ষড়যন্ত্র
    0.52
     सिंहासन
    0.51
    वेशन
    0.51
    Activations Density 0.001%

    No Known Activations