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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49836
    Prev
    Next
    INDEX
    Explanations

    malaria and Plasmodium falciparum

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

    fever reduction

    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
    Not in Any Lists

    No Comments

    Negative Logits
    อากาศ
    0.49
     muffin
    0.46
     Eros
    0.42
     Craft
    0.41
    面包
    0.41
     muffins
    0.41
    雏
    0.41
    라인
    0.41
     Baek
    0.41
     Aeros
    0.40
    POSITIVE LOGITS
     Malaria
    0.70
     malaria
    0.69
    疟
    0.54
     मले
    0.53
    瘧
    0.52
     demon
    0.44
    GM
    0.43
    SY
    0.42
     fever
    0.41
     Fever
    0.41
    Activations Density 0.023%

    No Known Activations