© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1337
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    这家
    0.63
     Format
    0.62
     Ral
    0.62
     ザ
    0.61
     מר
    0.61
    잔
    0.61
    பூ
    0.60
     무엇
    0.60
     niez
    0.59
     MR
    0.59
    POSITIVE LOGITS
    stwo
    0.76
    sc
    0.66
    stm
    0.61
    ст
    0.59
    ST
    0.59
    tabs
    0.57
    ஸ்ட்
    0.57
    št
    0.57
    SCs
    0.56
    ισ
    0.56
    Activations Density 0.250%

    No Known Activations