© 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. 10854
    Prev
    Next
    INDEX
    Explanations

    companies and sectors

    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
    iség
    0.95
     jeg
    0.93
    πι
    0.92
     Dys
    0.90
     jag
    0.88
    면
    0.87
     kome
    0.86
     Hog
    0.86
     stow
    0.86
     Cuz
    0.85
    POSITIVE LOGITS
    marie
    1.13
    leaf
    1.05
    mont
    1.04
     rừng
    0.99
    tree
    0.95
    嶺
    0.95
    wood
    0.93
     thorny
    0.92
     wood
    0.92
     tree
    0.91
    Activations Density 0.198%

    No Known Activations