© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    too + descriptor

    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
    ${
    1.67
     envol
    1.67
     LoginComponent
    1.63
    assertEqual
    1.62
    ้
    1.61
    na
    1.59
    й
    1.58
    ❤️❤️
    1.54
     vart
    1.54
     resembling
    1.53
    POSITIVE LOGITS
    𝘄
    1.69
    회의
    1.67
    Он
    1.66
    Ngoài
    1.61
    ग्रस्त
    1.59
    НУ
    1.54
    См
    1.52
    вки
    1.51
    Audi
    1.50
     વખતે
    1.49
    Activations Density 0.033%

    No Known Activations