© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13629
    Prev
    Next
    INDEX
    Explanations

    seemed surprised

    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_13_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
     slows
    1.75
     bottlenecks
    1.64
     attributed
    1.50
     derives
    1.45
    attributed
    1.41
    <0xA2>
    1.38
     ascribed
    1.38
     slow
    1.37
     sluggish
    1.33
     counted
    1.33
    POSITIVE LOGITS
    ン
    2.23
    लभ
    2.09
    داری
    2.07
    ل
    2.06
    ن
    2.02
    zeczytaj
    2.02
    لین
    1.88
    рте
    1.87
    uose
    1.84
    ার
    1.81
    Activations Density 0.070%

    No Known Activations