© 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. 2010
    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
     যথা
    0.77
    েরই
    0.69
    ]/(
    0.67
     رسمي
    0.65
    ologisk
    0.64
     میکرز
    0.63
     అంతే
    0.63
    )]^{
    0.63
    лосо
    0.63
    とも
    0.62
    POSITIVE LOGITS
     while
    5.51
    while
    5.12
     mientras
    4.81
     WHILE
    4.73
     whilst
    4.70
     mentre
    4.50
     While
    4.42
    While
    4.40
     enquanto
    4.27
     während
    4.16
    Activations Density 2.204%

    No Known Activations