© 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. 218122
    Prev
    Next
    INDEX
    Explanations

    legal terms, measurements, identifiers

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

    medical conditions and artistic forms

    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
     टे
    0.50
    梦想
    0.49
     beauties
    0.47
     گوئیاں
    0.44
    енера
    0.44
    屼
    0.42
     thẳng
    0.42
     करीब
    0.42
    ناد
    0.42
     घ्यावी
    0.42
    POSITIVE LOGITS
     secre
    0.48
     appliqué
    0.48
    Ｊ
    0.46
    RIBUT
    0.45
     J
    0.43
     medically
    0.43
    IL
    0.42
     homage
    0.42
     querying
    0.42
    ঙ্কে
    0.42
    Activations Density 0.001%

    No Known Activations