© 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. 255592
    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
     an
    0.54
     European
    0.53
     six
    0.52
     advanced
    0.51
     Höhen
    0.51
     SIX
    0.50
     currency
    0.48
     သ
    0.48
     Superior
    0.48
     Trinidad
    0.48
    POSITIVE LOGITS
     постепенно
    0.49
    ोम
    0.48
     दह
    0.46
    Zip
    0.45
    Meal
    0.45
    Zach
    0.44
    SetStr
    0.44
    Работа
    0.44
    чев
    0.43
    Ң
    0.43
    Activations Density 0.001%

    No Known Activations