© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4148
    Prev
    Next
    INDEX
    Explanations

    PyTorch neural network code

    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
    Negative Logits
    술
    1.65
     wunder
    1.61
    唱歌
    1.60
     duk
    1.53
    스럽
    1.50
     тер
    1.48
    ஶ
    1.47
    곡
    1.45
    開き
    1.43
    社交
    1.43
    POSITIVE LOGITS
    Servlet
    1.94
    ERCE
    1.91
    ResponseWriter
    1.86
    affle
    1.86
    WebHost
    1.84
    carbox
    1.83
    pload
    1.82
    женности
    1.77
     ATPase
    1.73
     antigens
    1.70
    Activations Density 0.051%

    No Known Activations