© 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-16K
    7. 3439
    Prev
    Next
    INDEX
    Explanations

    news and encyclopedic sources

    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_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
     обме
    0.74
     માર
    0.64
    действие
    0.64
    ্নান
    0.63
     मिलेगी
    0.62
    داء
    0.61
    డు
    0.61
    {[
    0.59
    갈
    0.59
     przej
    0.59
    POSITIVE LOGITS
     BBC
    1.74
     Smithsonian
    1.67
    BBC
    1.46
     CNN
    1.44
     Britannica
    1.41
     PBS
    1.39
     CNBC
    1.33
    bbc
    1.30
     NPR
    1.28
    CNN
    1.27
    Activations Density 0.076%

    No Known Activations