© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75557
    Prev
    Next
    INDEX
    Explanations

    seek doctor's advice

    np_acts-logits-general · gemini-2.5-flash-lite

    consult your doctor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ellingen
    0.40
     زندہ
    0.40
     vêtements
    0.38
     człowieka
    0.38
    acaks
    0.38
     terminer
    0.38
     wodurch
    0.37
     แสดง
    0.37
    時から
    0.37
    🚪
    0.37
    POSITIVE LOGITS
     consult
    0.79
     consulted
    0.72
     Consult
    0.71
     konsult
    0.71
    consult
    0.68
     consultar
    0.67
    Consult
    0.67
    相談
    0.63
    咨询
    0.61
     consultation
    0.60
    Activations Density 0.161%

    No Known Activations