© 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. 221177
    Prev
    Next
    INDEX
    Explanations

    fully funded

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

    Windows 11 Pro keys

    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
    ід
    0.58
    얄
    0.56
    arı
    0.52
    ブリッド
    0.49
    سرائيل
    0.49
    Coleman
    0.48
     toàn
    0.47
     TensorFlow
    0.47
    Ç
    0.47
    データを
    0.46
    POSITIVE LOGITS
     undercover
    0.43
     pemer
    0.42
     கண்டு
    0.42
    too
    0.42
     kelompok
    0.42
    |}{
    0.41
     administ
    0.41
    steil
    0.41
     प्रशा
    0.41
     組
    0.41
    Activations Density 0.001%

    No Known Activations