© 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-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1911
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preservatives
    0.73
     transmettre
    0.72
     サマータイヤ
    0.68
    传递
    0.66
    язви
    0.65
    短暂
    0.65
     Honorary
    0.65
     共
    0.65
     curto
    0.62
     printers
    0.62
    POSITIVE LOGITS
     intuitive
    1.63
    Intu
    1.49
    intuitive
    1.49
    Powerful
    1.49
     intuit
    1.48
     Intu
    1.47
     powerful
    1.46
    powerful
    1.42
     Powerful
    1.37
     puissant
    1.37
    Activations Density 1.652%

    No Known Activations