© 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. 206143
    Prev
    Next
    INDEX
    Explanations

    Diageo liquor brands

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

    is often, is a, tuned version, game name

    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
    인
    0.53
    
    0.53
    י
    0.52
    이
    0.50
    ра
    0.49
    არ
    0.47
    ਤੀ
    0.47
     시
    0.47
    і
    0.47
    ע
    0.47
    POSITIVE LOGITS
     officielles
    0.54
     mắn
    0.50
     marshm
    0.47
     marshmallows
    0.46
     workflows
    0.46
     minions
    0.45
     mdl
    0.45
    vspace
    0.44
     pesto
    0.44
     Physiology
    0.44
    Activations Density 0.000%

    No Known Activations