© 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. 221241
    Prev
    Next
    INDEX
    Explanations

    piercing context

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

    commit to game development

    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
     penggunaan
    0.47
    جيل
    0.46
     käyttö
    0.45
    ガラス
    0.44
     jato
    0.44
    DD
    0.43
    jadi
    0.42
    搔
    0.42
    apy
    0.42
    ό
    0.41
    POSITIVE LOGITS
     четы
    0.57
     кален
    0.51
     देयर
    0.50
     ክ
    0.50
     разделить
    0.49
     Reflection
    0.46
     כול
    0.46
     reflection
    0.45
     服
    0.45
     வரலாற்று
    0.45
    Activations Density 0.001%

    No Known Activations