© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 8689
    Prev
    Next
    INDEX
    Explanations

    tkinter as tk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     น
    1.56
    َ
    1.55
     حتى
    1.45
    ال
    1.44
     ن
    1.40
     อิน
    1.39
     ก
    1.38
     ще
    1.38
    ธุ์
    1.38
     ต
    1.38
    POSITIVE LOGITS
     refuge
    1.43
     bench
    1.41
     objekt
    1.35
     ridicule
    1.32
     recommandé
    1.32
     initiative
    1.31
     basso
    1.31
     marm
    1.31
     franchise
    1.31
     Batu
    1.30
    Activations Density 0.000%

    No Known Activations