© 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. 258994
    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
    ས་
    0.53
    יא
    0.50
     капитала
    0.48
    ლა
    0.47
    ności
    0.47
    ש
    0.47
     fyr
    0.46
     campagna
    0.44
    沚
    0.44
    cı
    0.44
    POSITIVE LOGITS
     rápidamente
    0.46
     กด
    0.42
     transporting
    0.41
    趟
    0.40
     transportar
    0.40
     rapidamente
    0.39
     escog
    0.39
    ọt
    0.38
     постепенно
    0.38
     jamming
    0.38
    Activations Density 0.002%

    No Known Activations