© 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-65K
    7. 3228
    Prev
    Next
    INDEX
    Explanations

    code and system metrics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ్రు
    0.61
     debo
    0.59
    躯
    0.57
    bib
    0.57
     weep
    0.56
    uiscono
    0.55
     subsec
    0.55
    ङ
    0.54
     मल
    0.54
    онер
    0.54
    POSITIVE LOGITS
     установ
    0.73
    قوم
    0.71
    навли
    0.70
    转换
    0.66
    টুকু
    0.65
     прове
    0.64
     서
    0.64
     promove
    0.63
    瀚
    0.63
     Из
    0.63
    Activations Density 0.066%

    No Known Activations