© 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. 226
    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
    <unused25>
    0.77
    ાર્થના
    0.74
    <unused280>
    0.74
    <unused6>
    0.73
     سایټ
    0.73
    ၻ
    0.72
    <unused9>
    0.72
    ClrBit
    0.72
    蘞
    0.72
    <unused42>
    0.72
    POSITIVE LOGITS
     tome
    0.81
     o
    0.79
     ot
    0.77
     doen
    0.75
    <0xC2>
    0.75
     thee
    0.71
      
    0.70
     fo
    0.69
     up
    0.69
    Continue
    0.69
    Activations Density 7.471%

    No Known Activations