© 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-65K
    7. 60977
    Prev
    Next
    INDEX
    Explanations

    health care, updates, computing, analysis

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ᄆ
    0.49
    GoObject
    0.47
    జే
    0.47
    ле
    0.45
    ᅦ
    0.44
     Acho
    0.43
    هن
    0.43
    링크
    0.43
    రే
    0.42
     Vorder
    0.42
    POSITIVE LOGITS
    prison
    0.46
    ḫ
    0.45
     अस्थ
    0.44
     स्वास्थ्य
    0.43
     علمی
    0.43
     judiciales
    0.43
    বারি
    0.43
     Marine
    0.43
     menjelaskan
    0.43
    τια
    0.41
    Activations Density 0.004%

    No Known Activations