© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101086
    Prev
    Next
    INDEX
    Explanations

    bloodstream infections, Johannes, Johnnie, currentTarget, mouseover

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

    The neuron is specifically detecting occurrences of the word “bloodstream,” especially in contexts like “bloodstream infections.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    s
    -3.30
    癀
    -2.73
    )
    -2.64
    i
    -2.42
     nästan
    -2.14
    י
    -2.13
    ی
    -2.13
    地的
    -2.13
     municipales
    -2.11
    t
    -2.09
    POSITIVE LOGITS
     anf
    2.55
    ).
    2.50
    霂
    2.45
    ⩥
    2.31
    能夠
    2.28
    
    2.28
     kleines
    2.27
    强行
    2.23
    鹟
    2.20
    轫
    2.19
    Activations Density 0.007%

    No Known Activations