© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101836
    Prev
    Next
    INDEX
    Explanations

    germ virulence factors

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

    words related to pathogenic microorganisms and their virulence factors.

    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
    vantaged
    -2.83
     mélange
    -2.31
    她
    -2.28
    〤
    -2.28
     dégustation
    -2.25
    午後
    -2.13
     russes
    -2.09
    昨日
    -2.09
    課程
    -2.06
    ...?
    -2.05
    POSITIVE LOGITS
    䜣
    2.83
    {
    2.81
    沕
    2.39
    毉
    2.28
    ⟝
    2.22
    
    2.20
    翆
    2.09
    ing
    2.06
     estudian
    2.03
    想不到
    2.02
    Activations Density 0.006%

    No Known Activations