© 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. 13590
    Prev
    Next
    INDEX
    Explanations

    code or filenames

    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
     Machinery
    0.97
     Linguistic
    0.91
    วัต
    0.89
     Фа
    0.86
    气体
    0.85
    Фа
    0.84
     Infra
    0.83
    :
    0.80
     باقي
    0.79
    了一眼
    0.79
    POSITIVE LOGITS
     christmas
    1.16
     xmas
    1.12
     sacking
    1.08
     halloween
    1.07
     schen
    1.06
     schol
    1.06
     क्रिसमस
    1.05
     customPlot
    1.03
     hiring
    1.02
     coupon
    1.02
    Activations Density 0.019%

    No Known Activations