© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 107435
    Prev
    Next
    INDEX
    Explanations

    fact checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    {\|
    0.57
    にと
    0.55
    णाल
    0.49
    れません
    0.48
     Criterion
    0.47
     to
    0.47
    {
    0.46
    ದುಕೊಳ್ಳ
    0.46
     বুঝি
    0.46
    Criterion
    0.45
    POSITIVE LOGITS
    ’
    0.67
    i
    0.60
    et
    0.59
    '
    0.57
    ed
    0.57
     criança
    0.56
    ET
    0.56
    en
    0.55
     Reverso
    0.54
     Mittag
    0.54
    Activations Density 0.003%

    No Known Activations