© 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. 254925
    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
     fama
    0.50
     |
    0.42
     aa
    0.42
     mappa
    0.42
     Kidney
    0.42
     &
    0.41
     qua
    0.41
     fur
    0.40
     khớp
    0.40
    рта
    0.40
    POSITIVE LOGITS
    ണിക്ക
    0.51
    국
    0.50
     dziew
    0.48
    团结
    0.48
    师
    0.46
    र्देश
    0.44
    Ал
    0.44
    С
    0.44
    年轻
    0.44
    Го
    0.43
    Activations Density 0.000%

    No Known Activations