© 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. 259579
    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
    段时间
    0.46
    ังหวัด
    0.44
    are
    0.44
    现代
    0.44
    면
    0.43
    най
    0.43
    那时候
    0.43
    当时的
    0.43
    ন
    0.43
    当下
    0.42
    POSITIVE LOGITS
     siete
    0.50
     sete
    0.49
     vrij
    0.47
    ﻈ
    0.47
     potencia
    0.46
     oficinas
    0.44
     cumpl
    0.44
     disponibilidad
    0.44
     preparazione
    0.43
     procedente
    0.43
    Activations Density 0.001%

    No Known Activations