© 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. 252451
    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
    کا
    0.52
    billion
    0.50
    ración
    0.48
    spaper
    0.48
    cached
    0.48
    kook
    0.48
    kerja
    0.48
    뢨
    0.47
     кеңсеси
    0.47
    dollar
    0.47
    POSITIVE LOGITS
     L
    0.50
     d
    0.49
     In
    0.49
     Lx
    0.48
     prenot
    0.48
     anormal
    0.47
     Л
    0.46
     D
    0.46
     д
    0.46
     ос
    0.45
    Activations Density 0.000%

    No Known Activations