© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1657
    Prev
    Next
    INDEX
    Explanations

    how to run

    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
    <blockquote>
    3.50
    ↵
    2.64
    achusetts
    2.39
     drier
    2.37
    險
    2.34
     conting
    2.24
     inch
    2.19
     м
    2.19
     bear
    2.15
    ாதாரண
    2.13
    POSITIVE LOGITS
     ентитету
    2.66
    ا
    2.54
    "},{"
    2.54
    Attached
    2.51
    ্ভব
    2.48
    വൃത്തി
    2.44
    न
    2.43
    tens
    2.43
     похађа
    2.42
    のが
    2.42
    Activations Density 0.013%

    No Known Activations