© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2064
    Prev
    Next
    INDEX
    Explanations

    UCLA, Los Angeles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     shaman
    0.88
     idempot
    0.83
     phishing
    0.80
     concaten
    0.78
     touchpad
    0.77
     geolocation
    0.76
     nemat
    0.76
     VMs
    0.76
    큥
    0.76
     nilpotent
    0.76
    POSITIVE LOGITS
    လ်
    0.43
    โ
    0.42
    エ
    0.40
    斯
    0.40
    แ
    0.38
    ˈ
    0.37
    스
    0.37
     แ
    0.37
     โ
    0.37
    డ్‌
    0.37
    Activations Density 0.102%

    No Known Activations