© 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. 71788
    Prev
    Next
    INDEX
    Explanations

    enteric bacteria and viruses

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

    The neuron activates for bacteria and pathogens, specifically focusing on enterococci and enteric bacteria in medical/scientific texts.

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

    The neuron strongly activates on mentions of “enteric” or “Enterococcus” (i.e. words beginning with “enter-” referring to enteric bacteria).

    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
    C
    -3.33
    2
    -3.19
    H
    -2.88
    W
    -2.69
    1
    -2.58
    3
    -2.58
    as
    -2.48
    9
    -2.47
    S
    -2.38
    M
    -2.34
    POSITIVE LOGITS
    瑨
    2.39
     dicha
    2.36
     sowohl
    2.22
    RIZ
    2.17
     imprimi
    2.13
    ğu
    2.13
     ciertos
    2.08
    ്
    2.08
    XIC
    2.06
     brinda
    2.06
    Activations Density 0.026%

    No Known Activations