© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2535
    Prev
    Next
    INDEX
    Explanations

    ](https

    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
     ולא
    1.87
     এবং
    1.86
     واست
    1.83
     and
    1.83
     и
    1.75
     或
    1.71
    ಲಿಲ್ಲ
    1.67
     eikä
    1.65
     squaring
    1.60
     awn
    1.60
    POSITIVE LOGITS
    amp
    2.14
    ndash
    2.08
    ╱
    1.93
    အတူ
    1.89
    ंगाबाद
    1.89
     seterusnya
    1.84
    mdash
    1.83
    iamo
    1.76
    REW
    1.76
    nbsp
    1.70
    Activations Density 0.473%

    No Known Activations