© 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. 260330
    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
     operable
    0.47
    antes
    0.47
    inology
    0.46
    एँ
    0.45
     रोहित
    0.44
     Fields
    0.43
     Schemes
    0.42
    柇
    0.42
     ऑपरेट
    0.42
    वारे
    0.41
    POSITIVE LOGITS
     damal
    0.56
     jab
    0.51
     sudd
    0.49
     neben
    0.47
     nuestro
    0.47
     Jacket
    0.47
     probablemente
    0.47
     nosso
    0.46
     stubborn
    0.46
     probably
    0.46
    Activations Density 0.000%

    No Known Activations