© 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. 260337
    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
     apapun
    0.55
     συνο
    0.52
    滕
    0.49
    стно
    0.48
    Delimiter
    0.47
     desempeño
    0.47
    мию
    0.47
    Preface
    0.46
    璞
    0.46
    郆
    0.46
    POSITIVE LOGITS
     blood
    0.50
     round
    0.50
    3
    0.50
     January
    0.50
     to
    0.49
    rounder
    0.49
    1
    0.49
     market
    0.48
     outlets
    0.46
    sheet
    0.46
    Activations Density 0.002%

    No Known Activations