© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1420
    Prev
    Next
    INDEX
    Explanations

    sets it apart

    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
     karşılaş
    1.70
     teljesen
    1.66
     termasuk
    1.50
     überras
    1.50
    veel
    1.49
     yaitu
    1.49
     hadden
    1.48
    家
    1.46
    izde
    1.46
     férfi
    1.44
    POSITIVE LOGITS
     CONFIG
    1.76
     OIL
    1.67
     savers
    1.66
    igrade
    1.63
    娀
    1.62
     AUTHOR
    1.62
    ׁ
    1.61
    loaders
    1.58
     STANDARD
    1.57
     Configuring
    1.56
    Activations Density 0.000%

    No Known Activations