© 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. 56639
    Prev
    Next
    INDEX
    Explanations

    stress, fear, sexual health

    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
    iate
    0.45
    até
    0.42
     abband
    0.42
    昼
    0.41
    ância
    0.41
    ías
    0.40
    ič
    0.40
    andinavian
    0.40
     licht
    0.39
    áz
    0.39
    POSITIVE LOGITS
     refinancing
    0.47
     выпуск
    0.42
    或許
    0.42
    и
    0.41
     финансо
    0.41
     رئیس
    0.40
     Oakland
    0.40
    꽈
    0.39
    購入
    0.39
    新たな
    0.38
    Activations Density 0.007%

    No Known Activations