© 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. 254528
    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
    不动
    0.50
    欵
    0.48
    zur
    0.48
    佉
    0.48
    oky
    0.47
    竍
    0.47
    鍾
    0.47
    璞
    0.46
    磬
    0.46
    क्ले
    0.46
    POSITIVE LOGITS
    mtd
    0.57
    sort
    0.53
     collectively
    0.48
     con
    0.48
     multifunctional
    0.48
    dept
    0.47
     şekilde
    0.46
     multid
    0.46
     multifunction
    0.45
     بین
    0.45
    Activations Density 0.002%

    No Known Activations