© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2955
    Prev
    Next
    INDEX
    Explanations

    annual earnings and refreshing technology

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    η
    3.08
     chiar
    2.95
    了一个
    2.88
     syukur
    2.88
    ्य
    2.64
     tiges
    2.63
    ษัท
    2.61
     noget
    2.61
    雰囲
    2.53
    कर्ता
    2.50
    POSITIVE LOGITS
    т
    5.36
    u
    4.80
    ر
    4.53
    te
    3.86
    s
    3.68
    ০
    3.58
    sion
    3.53
    o
    3.49
    e
    3.46
    이
    3.39
    Activations Density 0.246%

    No Known Activations