© 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. 10583
    Prev
    Next
    INDEX
    Explanations

    hypothalamic-pituitary-adrenal axis, influenza

    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
     Euclidean
    1.80
     put
    1.71
    اس
    1.69
     say
    1.62
     precise
    1.61
    ลา
    1.60
     speculate
    1.56
    ÷
    1.53
     proportion
    1.52
     correct
    1.52
    POSITIVE LOGITS
    esha
    2.67
    esi
    2.47
    ního
    2.37
    тік
    2.33
    lük
    2.29
    gara
    2.28
    urando
    2.27
    stagram
    2.26
    nang
    2.25
    tic
    2.24
    Activations Density 0.001%

    No Known Activations