© 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. 8372
    Prev
    Next
    INDEX
    Explanations

    tkinter and ttk

    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
    breve
    0.49
    ăl
    0.49
    씽
    0.48
     frecuente
    0.47
    famous
    0.46
    preg
    0.46
    bone
    0.45
    cnx
    0.45
    恒
    0.45
    finite
    0.45
    POSITIVE LOGITS
     sein
    0.55
     verl
    0.55
     sparkle
    0.52
     Nets
    0.52
     lashes
    0.52
     konte
    0.52
     laut
    0.51
     Hersteller
    0.51
     saam
    0.51
     kostet
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.