© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128240
    Prev
    Next
    INDEX
    Explanations

    chloroquine treatment

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

    pharmaceutical and medical drug names, particularly antimalarial drugs like chloroquine.

    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_10/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
    f
    -2.17
     '
    -1.94
    ;
    -1.87
     очень
    -1.84
     ('
    -1.84
    c
    -1.83
     has
    -1.83
    :])
    -1.82
    })
    -1.81
    </h5>
    -1.80
    POSITIVE LOGITS
     zitate
    2.03
     lanka
    1.97
     Chambres
    1.96
     nuov
    1.92
    quelles
    1.90
     pérd
    1.88
     oxu
    1.88
     nahil
    1.88
    狴
    1.87
     jezt
    1.84
    Activations Density 0.027%

    No Known Activations