© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 3163
    Prev
    Next
    INDEX
    Explanations

    overlay=true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    abhavam
    0.46
     গার্ডিয়ান
    0.41
    ንስ
    0.39
     регулярно
    0.39
    etition
    0.39
    arasi
    0.39
     उन्नति
    0.38
     सिस्टम
    0.38
     remit
    0.38
    褰
    0.38
    POSITIVE LOGITS
    مد
    0.49
    Не
    0.45
    مو
    0.43
    О
    0.43
    Ⲟ
    0.43
    ிக
    0.43
    包
    0.43
    इ
    0.40
    Во
    0.39
    Known
    0.39
    Activations Density 0.000%

    No Known Activations