© 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. 255605
    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
    在
    0.54
     დ
    0.50
     无
    0.49
     полной
    0.49
     in
    0.46
    ﺩ
    0.45
    稱
    0.44
    6
    0.44
    碧
    0.44
    м
    0.44
    POSITIVE LOGITS
    himanyu
    0.49
     RECEIPTS
    0.48
     Интере
    0.45
     gravit
    0.44
     Chur
    0.43
    thren
    0.43
    انات
    0.43
     membaca
    0.43
    culis
    0.43
     melakukan
    0.42
    Activations Density 0.001%

    No Known Activations