© 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. 257006
    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
     這
    0.59
     與
    0.56
    ኛውም
    0.55
     Johannesburg
    0.52
     設定
    0.51
     使い
    0.50
     由于
    0.49
    ವುದ
    0.49
    त्स
    0.48
     വേണ്ടി
    0.48
    POSITIVE LOGITS
    N
    0.54
    Lunch
    0.52
    Bank
    0.51
    Lab
    0.50
    So
    0.50
    Pharm
    0.49
    Na
    0.49
    Mur
    0.48
    Lar
    0.48
    );
    0.48
    Activations Density 0.000%

    No Known Activations