© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11164
    Prev
    Next
    INDEX
    Explanations

    try...finally blocks

    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_7_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
    Vie
    2.69
    லாமல்
    2.65
    gulpfile
    2.62
    beren
    2.32
    ায়ে
    2.30
     ét
    2.30
    пански
    2.26
    ⓗ
    2.20
    ায়ত্ত
    2.20
    EOL
    2.17
    POSITIVE LOGITS
    िस्थित
    3.64
    cionario
    3.09
    ي
    2.93
    ंपरिक
    2.88
    রা
    2.85
    inya
    2.85
    keiten
    2.74
    ípios
    2.70
    ंत्रिकी
    2.60
    ょう
    2.58
    Activations Density 0.021%

    No Known Activations