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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 82
    Prev
    Next
    INDEX
    Explanations

    playtime begins

    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
     PostgreSQL
    1.20
     liquors
    1.19
     دانشج
    1.08
     rượu
    1.07
     PLHIV
    1.06
     ಆತ್ಮ
    1.05
     postgres
    1.05
    酒
    1.05
     मतदारसंघात
    1.04
     empresario
    1.04
    POSITIVE LOGITS
     toddlers
    3.03
     preschool
    3.00
     toddler
    2.97
     preschoolers
    2.97
     Preschool
    2.92
     infants
    2.52
     infant
    2.49
     kindergarten
    2.47
     Kindergarten
    2.42
    幼儿
    2.42
    Activations Density 4.072%

    No Known Activations