© 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. 9091
    Prev
    Next
    INDEX
    Explanations

    international cooperation and relations

    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
     ശരീര
    0.58
    焦虑
    0.54
     അവസ്ഥ
    0.53
    恐惧
    0.52
    锤
    0.51
    뮬
    0.51
    周围
    0.50
     శరీ
    0.50
     प्रवृत्ति
    0.50
    鱼
    0.49
    POSITIVE LOGITS
     bilateral
    0.99
    mutual
    0.94
     cooperation
    0.93
     mutual
    0.93
     embassy
    0.92
     bilater
    0.89
     Embassy
    0.88
     reciprocal
    0.82
     diplomats
    0.82
    Mutual
    0.81
    Activations Density 0.057%

    No Known Activations