© 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. 81216
    Prev
    Next
    INDEX
    Explanations

    Prague academic publications

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

    Verification, brokers, responsibilities, definition

    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
     неу
    0.54
    㶲
    0.50
    Defaults
    0.49
    檤
    0.48
    㧋
    0.48
    няў
    0.46
    onato
    0.46
    㪯
    0.46
     ترلاسه
    0.45
    мония
    0.45
    POSITIVE LOGITS
     researches
    0.55
     McDonalds
    0.48
     amongst
    0.46
     Seats
    0.45
     whilst
    0.45
     jean
    0.45
    t
    0.45
    ll
    0.45
     ardent
    0.45
     yanında
    0.44
    Activations Density 0.000%

    No Known Activations