© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4618
    Prev
    Next
    INDEX
    Explanations

    lung, breast, childhood, bowel cancer

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

    cancer

    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_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hydraul
    0.45
    僳
    0.45
     Trench
    0.43
     blacksmith
    0.42
     Tren
    0.42
     silverware
    0.42
     cutlery
    0.41
    🥢
    0.41
     sleigh
    0.40
    湟
    0.40
    POSITIVE LOGITS
     cancer
    3.94
    Cancer
    3.70
    cancer
    3.69
     Cancer
    3.56
     cancers
    3.45
     कैंसर
    3.44
     cancerous
    3.42
     cáncer
    3.39
     kanker
    3.27
    癌症
    3.25
    Activations Density 0.358%

    No Known Activations