© 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. 258864
    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
     während
    0.54
    k
    0.52
     unmarried
    0.51
     bay
    0.50
     zgod
    0.49
     entsprechend
    0.48
     échelle
    0.48
     entschied
    0.47
     baz
    0.47
    kul
    0.46
    POSITIVE LOGITS
    碚
    0.50
    osevelt
    0.50
    ົວ
    0.49
    १९
    0.47
    िन
    0.46
     ফিরিয়ে
    0.46
     टैबलेट
    0.46
     यूरो
    0.45
     duplicating
    0.45
    ırlar
    0.44
    Activations Density 0.001%

    No Known Activations