© 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. 9832
    Prev
    Next
    INDEX
    Explanations

    prints to the console

    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
     dígitos
    1.04
     cerca
    1.04
     വിദ്യാ
    1.03
     προσ
    1.01
    ﾖ
    1.00
     matemáticas
    1.00
     bebés
    0.99
     玉
    0.98
    🇺
    0.97
     dünya
    0.96
    POSITIVE LOGITS
    example
    1.10
    lvmama
    1.10
    Example
    0.90
    atgu
    0.88
    company
    0.87
    Company
    0.87
    Description
    0.85
     Company
    0.84
    corder
    0.83
    calar
    0.82
    Activations Density 0.003%

    No Known Activations