© 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. 254742
    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
    ublik
    0.54
    クリル
    0.47
     グ
    0.47
    {|
    0.46
     کي
    0.45
    raded
    0.45
    ró
    0.45
    írus
    0.45
    鈺
    0.45
     পত্রিকা
    0.44
    POSITIVE LOGITS
     episodes
    0.46
     face
    0.45
     Faces
    0.44
     Murn
    0.44
     Liner
    0.44
     Assumptions
    0.44
     Ques
    0.43
     comparisons
    0.43
     dese
    0.43
     das
    0.42
    Activations Density 0.001%

    No Known Activations