© 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. 1268
    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
     আক্রমণে
    0.72
    붉
    0.71
     pripre
    0.69
     तैयारियों
    0.69
     descriptor
    0.68
     prévention
    0.67
     確認
    0.66
     fels
    0.66
     preparedness
    0.66
     подготовки
    0.66
    POSITIVE LOGITS
     profits
    2.92
     earn
    2.90
     earning
    2.88
     profit
    2.88
    賺
    2.85
    赚
    2.79
     earns
    2.79
     earnings
    2.75
    赚钱
    2.72
     profitable
    2.70
    Activations Density 1.459%

    No Known Activations