© 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. 721
    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
     rainbows
    0.79
    စိတ်
    0.76
     피해
    0.73
    pheromone
    0.72
     hemolysis
    0.72
     heuristic
    0.71
     montage
    0.71
    楹
    0.71
     matahari
    0.70
    তাবাদ
    0.70
    POSITIVE LOGITS
     thick
    2.24
    thick
    1.80
     firm
    1.74
     dense
    1.73
     soft
    1.70
     thicker
    1.68
     Thick
    1.62
     stiff
    1.61
     thin
    1.57
     plump
    1.55
    Activations Density 1.702%

    No Known Activations