© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32929
    Prev
    Next
    INDEX
    Explanations

    cervical screening programme

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

    medical screening programs and procedures, particularly related to cancer detection.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    énie
    -0.89
    odendron
    -0.85
     Pediatric
    -0.84
     못
    -0.79
    uyên
    -0.79
    nières
    -0.79
     penerbangan
    -0.78
    السلام
    -0.78
    essori
    -0.77
     télécommande
    -0.77
    POSITIVE LOGITS
     screening
    2.22
     Screening
    1.71
    Screening
    1.62
     screen
    1.55
    screening
    1.49
     SCREEN
    1.42
     screenings
    1.41
     Screen
    1.40
    SCREEN
    1.29
     screened
    1.29
    Activations Density 0.142%

    No Known Activations