© 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. 260432
    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
    偿
    0.46
     كلمات
    0.45
    噬
    0.44
    MaxWidth
    0.44
     sicht
    0.43
     Babylon
    0.43
     Avner
    0.43
    丛
    0.42
    leet
    0.42
    auten
    0.42
    POSITIVE LOGITS
     canoe
    0.54
     entrée
    0.49
     paddle
    0.48
     centerpiece
    0.47
     apare
    0.46
     ACLU
    0.46
     paddles
    0.46
     détente
    0.46
     para
    0.45
     domic
    0.45
    Activations Density 0.001%

    No Known Activations