© 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. 158812
    Prev
    Next
    INDEX
    Explanations

    projects and entities

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

    project proposals and demand

    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
    size
    0.46
    രിച്ചത്
    0.46
    use
    0.43
     হেঁটে
    0.43
     using
    0.42
     (
    0.41
     to
    0.40
     size
    0.40
     uses
    0.40
     Shanghai
    0.39
    POSITIVE LOGITS
    课堂
    0.52
    Popul
    0.52
    工事
    0.50
     проектов
    0.49
    Proble
    0.48
     અમારા
    0.48
    爭
    0.47
     ہمارا
    0.46
    人和
    0.46
     করিতেছেন
    0.46
    Activations Density 0.001%

    No Known Activations