© 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. 255347
    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
    🗨
    0.54
     ภาพ
    0.52
     การ
    0.50
     görüntü
    0.50
    SXml
    0.49
    િયલ
    0.49
     تصاویر
    0.49
    یدم
    0.49
     ifade
    0.48
     WeChat
    0.48
    POSITIVE LOGITS
    é
    0.53
    addies
    0.52
     nationals
    0.51
    leys
    0.51
    ikum
    0.49
    geon
    0.47
    icksburg
    0.47
     residentes
    0.46
    itis
    0.46
    handlers
    0.46
    Activations Density 0.000%

    No Known Activations