© 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. 253674
    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
    alphas
    0.48
    ($(
    0.43
    르
    0.43
    Dos
    0.41
    fc
    0.41
    긔
    0.40
    xcodep
    0.40
     ঠিকানা
    0.40
    YO
    0.40
    Ξ
    0.40
    POSITIVE LOGITS
     handover
    0.52
     detention
    0.52
     gyárt
    0.49
     staff
    0.48
     करून
    0.48
     exon
    0.48
     outpost
    0.48
     repatriation
    0.47
     pow
    0.47
     confection
    0.47
    Activations Density 0.001%

    No Known Activations