© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11686
    Prev
    Next
    INDEX
    Explanations

    list management or task lists

    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
    1.04
     ancient
    1.01
     n
    0.99
     you
    0.98
     dark
    0.96
     You
    0.96
     sweet
    0.94
     xo
    0.94
     A
    0.93
     time
    0.92
    POSITIVE LOGITS
     hinsichtlich
    1.51
    echolog
    1.47
    iranja
    1.44
    ორციელ
    1.40
    রন
    1.39
     সেনাবাহ
    1.38
    ována
    1.38
    ariye
    1.36
    rbrakk
    1.34
     Motorsports
    1.33
    Activations Density 0.000%

    No Known Activations