© 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. 113091
    Prev
    Next
    INDEX
    Explanations

    bloodstream infections

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

    references to 'bloodstream' and data-related terms in medical or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is specifically detecting appearances of the word “bloodstream.”

    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
    ).
    -2.56
    “
    -2.55
            
    -2.33
     of
    -2.31
     novembro
    -2.20
     fueled
    -2.20
    }
    -2.17
     scrutin
    -2.17
    鋲
    -2.14
    十七
    -2.11
    POSITIVE LOGITS
    on
    2.86
    r
    2.52
    〰
    2.47
     vostra
    2.45
    ⾞
    2.41
    再び
    2.34
    閦
    2.33
     edile
    2.30
    我
    2.28
    Szia
    2.22
    Activations Density 0.006%

    No Known Activations