© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8282
    Prev
    Next
    INDEX
    Explanations

    public health interventions

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

    prevention and intervention

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ্ডার
    0.44
     వ్యవస్థ
    0.42
     طرح
    0.41
     Espresso
    0.40
    Firing
    0.40
     tượng
    0.39
     อนุ
    0.39
     নিরাপত্তা
    0.38
    㕮
    0.38
    轧
    0.38
    POSITIVE LOGITS
     tobacco
    0.70
     interventions
    0.68
    Tobacco
    0.68
     Tobacco
    0.67
     epidemi
    0.66
     Prevention
    0.64
     CDC
    0.64
     intervention
    0.64
     prevention
    0.64
     obesity
    0.62
    Activations Density 0.276%

    No Known Activations