© 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. 31-GEMMASCOPE-2-RES-262K
    7. 48494
    Prev
    Next
    INDEX
    Explanations

    "I" + understand/like/can

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    اني
    0.45
     मुझ
    0.43
     WEST
    0.43
    今回は
    0.41
     যতক্ষণ
    0.41
    我对
    0.41
    我又
    0.41
     நான்
    0.40
     मैं
    0.40
     ヒ
    0.40
    POSITIVE LOGITS
     già
    0.42
     significativo
    0.40
     mediante
    0.39
    ود
    0.39
     schon
    0.39
     sudah
    0.39
     estimado
    0.38
     επί
    0.38
    trad
    0.38
    не
    0.37
    Activations Density 0.064%

    No Known Activations