© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1637
    Prev
    Next
    INDEX
    Explanations

    avoids direct action

    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
    Negative Logits
     necessarily
    1.02
     necessariamente
    0.92
    eworthy
    0.91
     obstante
    0.90
     necesariamente
    0.90
    withstanding
    0.88
    zsche
    0.85
    ícias
    0.84
    tingham
    0.81
    楂
    0.81
    POSITIVE LOGITS
    詳細は
    0.65
    $<
    0.64
    นอก
    0.63
    mostly
    0.62
    いくつかの
    0.62
    non
    0.62
     Alternate
    0.62
     също
    0.62
    e
    0.62
     різних
    0.61
    Activations Density 0.108%

    No Known Activations