© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9169
    Prev
    Next
    INDEX
    Explanations

    filenames in code

    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
    0
    1.09
     Add
    0.95
    2
    0.92
    4
    0.91
    5
    0.89
     @
    0.88
    Int
    0.88
     NE
    0.87
    B
    0.87
     క్
    0.87
    POSITIVE LOGITS
    glightbox
    1.27
     staunch
    1.09
     chronically
    1.08
     parthenogenetic
    1.06
     chromospheres
    1.06
    themealdb
    1.06
     katva
    1.06
    hiqdev
    1.04
     complacency
    1.04
    slidesPerGroup
    1.03
    Activations Density 0.070%

    No Known Activations