© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185670
    Prev
    Next
    INDEX
    Explanations

    convinces or states conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    expansion, decomposition, efficiently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ようになって
    0.51
    bib
    0.50
    process
    0.49
    K
    0.49
     motocicleta
    0.48
    genus
    0.47
    M
    0.47
    になりました
    0.46
    diagnostic
    0.46
    ようになりました
    0.46
    POSITIVE LOGITS
     convinces
    0.48
     Decomposition
    0.48
     fireworks
    0.47
     Colours
    0.47
     wafers
    0.47
     Quakers
    0.47
    ఊ
    0.46
     horrors
    0.43
     arrows
    0.43
     Thousands
    0.43
    Activations Density 0.001%

    No Known Activations