© 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. 259391
    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
    ศัก
    0.48
    朼
    0.48
    块
    0.47
     لكن
    0.46
     cuanto
    0.46
     Biblia
    0.46
    笺
    0.46
    же
    0.46
    "=>$
    0.46
    宀
    0.45
    POSITIVE LOGITS
     flags
    0.46
    tired
    0.46
     TFS
    0.45
    yas
    0.44
     partito
    0.43
     Yol
    0.43
     weaknesses
    0.42
    ying
    0.42
     widths
    0.42
     rung
    0.42
    Activations Density 0.004%

    No Known Activations