© 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
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9681
    Prev
    Next
    INDEX
    Explanations

    Russian, Danish, and programming contexts

    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_22_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
    нды
    0.87
    झा
    0.87
     closeModal
    0.86
     THINGS
    0.85
    鍗
    0.84
    사를
    0.81
     effortlessly
    0.81
     things
    0.80
    (',',$
    0.78
    شاف
    0.78
    POSITIVE LOGITS
    apis
    1.01
    emen
    0.95
    avno
    0.94
    inguém
    0.92
    qk
    0.91
     Linking
    0.90
    គុ
    0.88
    ascape
    0.88
    iousness
    0.87
    ützen
    0.87
    Activations Density 0.021%

    No Known Activations