© 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. 17-GEMMASCOPE-2-RES-16K
    7. 14106
    Prev
    Next
    INDEX
    Explanations

    demonstrative purposes

    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_17_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
    ใน
    1.04
    の
    1.02
    が
    0.98
    ในการ
    0.98
    Ш
    0.96
     Throughout
    0.93
     для
    0.93
     nelle
    0.91
    А
    0.91
     एवं
    0.91
    POSITIVE LOGITS
     larger
    0.78
     사람
    0.78
     new
    0.75
     people
    0.74
     koris
    0.73
     two
    0.73
     the
    0.73
    rester
    0.72
     controversial
    0.72
     glorious
    0.71
    Activations Density 0.003%

    No Known Activations