© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2435
    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
    陶瓷
    0.58
    posure
    0.58
     ಪ
    0.58
     Distrito
    0.58
    セラ
    0.57
    Dt
    0.57
     DIST
    0.57
    pkey
    0.56
    ℙ
    0.56
     ایم
    0.55
    POSITIVE LOGITS
    authorization
    0.64
     авто
    0.62
    ransfer
    0.61
    brides
    0.60
    rahm
    0.60
     Autor
    0.58
    frid
    0.58
     экономической
    0.57
     jellyfish
    0.56
     décl
    0.56
    Activations Density 0.137%

    No Known Activations