© 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. 1333
    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
    ÇÕES
    1.04
    mera
    1.03
    lerini
    1.02
    lerine
    1.02
    ENTES
    1.01
    ﺨ
    0.99
    ﺠ
    0.97
    larına
    0.96
    нении
    0.95
    ulata
    0.94
    POSITIVE LOGITS
    ן
    0.96
    ிர்
    0.75
    ין
    0.75
    പ്പ്
    0.71
    ь
    0.70
    i
    0.68
    ாப்
    0.68
    in
    0.67
    an
    0.67
    й
    0.66
    Activations Density 1.824%

    No Known Activations