© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3550
    Prev
    Next
    INDEX
    Explanations

    stock exchange

    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
    ۣ
    1.75
     näher
    1.75
    orderEntry
    1.71
    ديد
    1.69
     dàng
    1.67
     regrowth
    1.65
    rootDir
    1.61
     q
    1.61
    럿
    1.60
    ddd
    1.60
    POSITIVE LOGITS
    सु
    1.91
    समा
    1.87
     Следу
    1.82
    Следу
    1.70
    boundaries
    1.65
    मोन
    1.64
     Options
    1.63
    нику
    1.63
     variations
    1.62
    াদান
    1.62
    Activations Density 0.000%

    No Known Activations