© 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. 14131
    Prev
    Next
    INDEX
    Explanations

    photo album or gift

    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
    ി
    2.42
    ாக
    2.34
    lung
    2.31
    সি
    2.22
    ீடு
    2.14
    inee
    2.13
    icc
    2.11
    NSY
    2.10
    ిన
    2.10
    oporosis
    2.08
    POSITIVE LOGITS
    addOn
    2.55
    즌
    2.35
    ﺍ
    2.29
    <bos>
    2.28
    ब्दिक
    2.28
    tochy
    2.24
     пое
    2.21
    ゥム
    2.15
    ы
    2.12
     QMessageBox
    1.99
    Activations Density 0.072%

    No Known Activations