© 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. 1010
    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
    そういう
    1.01
     diffère
    0.98
     sufficiently
    0.97
    😕
    0.96
     relativamente
    0.95
    😑
    0.94
    😒
    0.94
    😐
    0.92
     מאוד
    0.91
     :/
    0.89
    POSITIVE LOGITS
     iconic
    1.88
     delectable
    1.86
     breathtaking
    1.76
     scrumptious
    1.75
     stunning
    1.66
     legendary
    1.65
     exciting
    1.63
     unforgettable
    1.62
     thrilling
    1.62
     renowned
    1.61
    Activations Density 2.074%

    No Known Activations