© 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. 68019
    Prev
    Next
    INDEX
    Explanations

    dengue fever virus

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

    mentions of dengue virus and related disease terminology.

    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
    ↵
    -3.66
     avec
    -3.05
    timbangan
    -2.39
     Then
    -2.38
     “
    -2.33
     với
    -2.31
    metheus
    -2.27
     ocurrir
    -2.25
     nuova
    -2.22
    }
    -2.22
    POSITIVE LOGITS
    捽
    2.89
    you
    2.56
    dersfield
    2.48
    羕
    2.47
    xically
    2.45
    ٭
    2.45
    ྅
    2.44
     土産
    2.36
     撮っ
    2.34
    oooooooo
    2.33
    Activations Density 0.001%

    No Known Activations