© 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. 87039
    Prev
    Next
    INDEX
    Explanations

    Tai Chi, character sequence, sensors

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

    risk and severity

    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
     MCU
    0.54
    選
    0.51
    高品質
    0.49
     Biden
    0.48
     Boho
    0.47
     AOS
    0.46
    寂
    0.46
     flat
    0.45
     crystall
    0.45
     OTT
    0.45
    POSITIVE LOGITS
     אל
    0.52
     llegando
    0.52
     ברי
    0.50
    nment
    0.48
     обучения
    0.47
     כאשר
    0.47
     הצ
    0.47
    ik
    0.46
    𝒏
    0.46
    space
    0.46
    Activations Density 0.000%

    No Known Activations