© 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. 15224
    Prev
    Next
    INDEX
    Explanations

    dengue virus or Tesco

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

    mentions of "dengue" or dengue-related terms in scientific or medical contexts.

    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
    ፨
    -2.73
    嫆
    -2.58
     obstruct
    -2.48
     escalate
    -2.41
    Ꭸ
    -2.38
     circumvent
    -2.38
     harness
    -2.38
    ⫘
    -2.36
    AutoresizingMask
    -2.33
     erode
    -2.33
    POSITIVE LOGITS
    {
    3.42
    -
    3.17
    =
    3.17
    >
    2.80
    0
    2.59
    (
    2.47
    .
    2.33
    +
    2.30
    %
    2.27
    "
    2.25
    Activations Density 0.006%

    No Known Activations