© 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-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2466
    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
    '।
    0.67
    ......
    0.64
    ल्यानंतर
    0.63
    晔
    0.63
    əd
    0.61
    ……
    0.60
    ्यो
    0.60
    jší
    0.60
     postpone
    0.60
     magari
    0.59
    POSITIVE LOGITS
     (`
    3.09
     (“
    3.04
     ($
    2.99
     ("
    2.94
     (€
    2.86
     (\"
    2.78
     ('
    2.75
     ($\
    2.74
     (‘
    2.73
     (@
    2.71
    Activations Density 0.936%

    No Known Activations