© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7159
    Prev
    Next
    INDEX
    Explanations

    running and jumping

    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
     Brock
    1.08
     Moll
    1.07
    钳
    1.01
    Brock
    0.99
    匏
    0.95
     Deane
    0.95
     Saturn
    0.94
     Pals
    0.94
    鉗
    0.93
    ◜
    0.93
    POSITIVE LOGITS
     RUN
    4.22
     running
    4.15
     run
    4.11
     Running
    4.04
    Run
    4.01
     Run
    4.01
    running
    3.94
    run
    3.88
    Running
    3.87
     runs
    3.86
    Activations Density 0.645%

    No Known Activations