© 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. 9894
    Prev
    Next
    INDEX
    Explanations

    m

    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
     LHS
    1.10
    省
    1.05
    州的
    1.03
    LH
    0.96
     Liga
    0.96
     LPS
    0.95
    DSL
    0.92
     LGA
    0.92
    MES
    0.91
    県の
    0.90
    POSITIVE LOGITS
     Championship
    0.91
     championship
    0.91
     opener
    0.91
    اؤ
    0.89
     newcomers
    0.88
     Championships
    0.85
    ო
    0.84
     openers
    0.84
     despacho
    0.84
     bekend
    0.83
    Activations Density 0.107%

    No Known Activations