© 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. 4640
    Prev
    Next
    INDEX
    Explanations

    pyplot and vscode imports

    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
     เออ
    1.38
     เอา
    1.30
     אטאטורק
    1.30
     האי
    1.27
    ,//
    1.26
    acetyl
    1.26
     കർ
    1.23
    powder
    1.22
    chés
    1.22
    ูล
    1.22
    POSITIVE LOGITS
     comparable
    1.12
     faster
    1.11
     a
    1.02
    s
    1.01
     much
    1.00
     similar
    0.98
     disparate
    0.98
     additional
    0.97
     or
    0.94
     many
    0.93
    Activations Density 0.000%

    No Known Activations