© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148002
    Prev
    Next
    INDEX
    Explanations

    command-line navigation and listing guide

    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_262k_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
     estimular
    0.81
    公共
    0.78
    跟踪
    0.75
    报警
    0.73
     (_.
    0.73
     átomos
    0.71
     reempl
    0.71
    ൽക
    0.71
    数据
    0.71
    稣
    0.70
    POSITIVE LOGITS
     Such
    0.95
     Guide
    0.92
     Guides
    0.86
     such
    0.84
    Such
    0.82
     Detailed
    0.81
    Guide
    0.81
     Documentation
    0.79
     Che
    0.78
     такое
    0.78
    Activations Density 0.001%

    No Known Activations