© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 441
    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
    <eos>
    1.38
    </blockquote>
    0.77
    <unused61>
    0.76
     […]
    0.66
    <h2>
    0.61
     Nonetheless
    0.59
     Furthermore
    0.59
    <unused63>
    0.59
     anyway
    0.58
     Anyway
    0.58
    POSITIVE LOGITS
     سلاٹ
    1.02
    唔
    0.96
     букмекерлар
    0.95
     букмекердик
    0.95
     سلاٹس
    0.94
     коюмдар
    0.92
     کیسینو
    0.90
     спорттук
    0.90
     казіно
    0.89
     фонбет
    0.88
    Activations Density 2.258%

    No Known Activations