© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6953
    Prev
    Next
    INDEX
    Explanations

    for the first / for a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    iotsit
    1.03
    ப்சீரி
    1.02
     keperluan
    1.02
     vuccatiti
    1.01
    StarSrvGroup
    1.01
    ꗫ
    1.01
    HtIdx
    1.01
    Polynucleaires
    1.01
    渦柱
    1.01
     sundry
    1.00
    POSITIVE LOGITS
    or
    0.92
    ch
    0.84
    OR
    0.76
    de
    0.72
     or
    0.72
    if
    0.70
    '
    0.69
     Box
    0.68
     is
    0.66
    ழ்
    0.63
    Activations Density 0.003%

    No Known Activations