© 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. 235693
    Prev
    Next
    INDEX
    Explanations

    internet talking

    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
    পত্রের
    0.52
     équipe
    0.50
     swoje
    0.48
     フォ
    0.48
    ̗
    0.47
     uvijek
    0.47
     elusive
    0.46
     étroite
    0.45
     impervious
    0.45
    কিন্ত
    0.45
    POSITIVE LOGITS
     Resolve
    0.45
    azem
    0.41
    ъм
    0.40
    auch
    0.39
     यर
    0.39
    ayev
    0.38
    및
    0.38
    抨
    0.38
     Belfast
    0.38
    CNN
    0.38
    Activations Density 0.001%

    No Known Activations