© 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. 107445
    Prev
    Next
    INDEX
    Explanations

    places, people, and concepts

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

    chain reaction

    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
     t
    0.50
     F
    0.50
     second
    0.44
    pm
    0.44
    x
    0.44
     T
    0.43
     i
    0.43
    人的
    0.43
     Farr
    0.43
    。
    0.42
    POSITIVE LOGITS
     نقط
    0.50
     жүктөп
    0.50
     TESTING
    0.49
     точка
    0.49
    Versioning
    0.48
     رياضيات
    0.48
    
    0.48
     καλύτε
    0.47
     চাহ
    0.47
     күзгү
    0.46
    Activations Density 0.001%

    No Known Activations