© 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. 3566
    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
    윰
    0.69
    ოვანი
    0.67
    ጅም
    0.64
    acijos
    0.63
    炆
    0.63
    戙
    0.62
    Ꮴ
    0.61
    莪
    0.60
     natale
    0.60
    ഞ്ഞ
    0.59
    POSITIVE LOGITS
    ip
    2.10
    pt
    2.02
    ipt
    1.91
    ps
    1.89
    ep
    1.82
    ips
    1.81
     ip
    1.76
    p
    1.72
    ప్
    1.69
    eps
    1.69
    Activations Density 0.589%

    No Known Activations