© 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. 221522
    Prev
    Next
    INDEX
    Explanations

    fuel-cell images, relational storm, metal reinforcing, traffic court, Link Quality

    np_acts-logits-general · gemini-2.5-flash-lite

    referrals and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    💿
    0.38
     इनसे
    0.37
    ण्डल
    0.37
    傳統
    0.36
    🥛
    0.36
    紅白
    0.36
     पुराने
    0.35
     قاعدة
    0.34
    ױ
    0.34
     такі
    0.34
    POSITIVE LOGITS
     debacle
    0.39
    മിന്റെ
    0.38
    As
    0.38
    人大
    0.38
    人之
    0.37
    oust
    0.36
     Gummies
    0.35
     Alej
    0.34
     racem
    0.34
    rarse
    0.34
    Activations Density 0.061%

    No Known Activations