© 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. 1891
    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
    сцю
    0.65
    ersham
    0.65
    ក្ខ
    0.63
    玠
    0.61
    డంతో
    0.59
    ृह
    0.59
    ेट्टी
    0.58
    ције
    0.57
    ostí
    0.57
    台中
    0.56
    POSITIVE LOGITS
     N
    3.12
     n
    3.05
    N
    3.00
    n
    2.79
    Ｎ
    2.49
    𝑁
    2.48
    ｎ
    2.47
     ن
    2.47
    𝑛
    2.44
    <0x98>
    2.40
    Activations Density 2.192%

    No Known Activations