© 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. 255561
    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
    พน
    0.50
    ษ
    0.49
    ಋ
    0.48
     שנים
    0.48
    欝
    0.47
    נו
    0.47
    מ
    0.47
    די
    0.46
    จาก
    0.46
    퍼
    0.46
    POSITIVE LOGITS
     Airbnb
    0.60
     journalists
    0.55
     ভ্রমণ
    0.54
     journalist
    0.54
     সাংবাদিক
    0.53
     periodista
    0.51
     여행
    0.51
     သင်
    0.50
     журнали
    0.50
     Journalist
    0.49
    Activations Density 0.003%

    No Known Activations