© 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. 256634
    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
    Мне
    0.55
     millón
    0.54
     niektó
    0.54
     액
    0.54
     உண்
    0.52
     escolher
    0.50
    我现在
    0.50
     empêcher
    0.50
     пен
    0.50
     znaleźć
    0.49
    POSITIVE LOGITS
     only
    0.86
    only
    0.77
     =
    0.68
     primarily
    0.68
     should
    0.65
     मुख्यतः
    0.65
     hanya
    0.65
    0.65
     seulement
    0.64
     केवल
    0.63
    Activations Density 0.034%

    No Known Activations