© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2377
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and results

    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_17_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
     LGBTQ
    1.62
    <0xC2>
    1.50
    ⁣
    1.49
     Healthcare
    1.37
    ​​
    1.36
    ‍
    1.33
    ​​​​
    1.32
     skincare
    1.28
     ✨
    1.26
    🤍
    1.25
    POSITIVE LOGITS
     hitherto
    1.78
     envisaged
    1.74
    不必
    1.70
    itherto
    1.68
     precluded
    1.66
    尤其
    1.63
     postulated
    1.61
     obvi
    1.58
     adduced
    1.58
     doubtless
    1.58
    Activations Density 0.261%

    No Known Activations