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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1715
    Prev
    Next
    INDEX
    Explanations

    'your' and 'my' placeholders

    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
    städ
    1.24
    cities
    1.04
     столи
    1.01
    =>
    1.01
    tiles
    1.00
    ☀
    0.99
     cérémon
    0.98
    province
    0.97
    küm
    0.97
    timers
    0.96
    POSITIVE LOGITS
     李
    1.06
     Daniel
    1.03
     James
    1.01
     Oppen
    0.99
     Jean
    0.99
     Stock
    0.97
     William
    0.96
     Ryan
    0.95
     Jeffrey
    0.95
     Johnson
    0.94
    Activations Density 0.241%

    No Known Activations