© 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. 119903
    Prev
    Next
    INDEX
    Explanations

    legislative or regulatory matters

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

    rarely a simple answer

    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
    🜨
    0.48
     gtag
    0.47
    ⟦
    0.46
    钢琴
    0.46
     வெப்பநிலை
    0.45
     أنواع
    0.45
     +#+
    0.43
     گوشی
    0.42
    ocèle
    0.42
    㞰
    0.42
    POSITIVE LOGITS
     Legislative
    0.52
     legislative
    0.51
     Convenience
    0.45
     informiert
    0.45
     prudent
    0.44
     Legislature
    0.44
     regulatory
    0.42
    ailing
    0.42
     deserve
    0.42
    undering
    0.42
    Activations Density 0.005%

    No Known Activations