© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73043
    Prev
    Next
    INDEX
    Explanations

    Salmonella

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

    This neuron detects mentions of Salmonella bacteria and related serotypes or diseases like salmonellosis.

    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
    </u>
    -2.63
     You
    -2.58
     "
    -2.55
    </h4>
    -2.41
     }
    -2.36
     What
    -2.16
     */
    -2.14
    9
    -2.13
    o
    -2.11
     That
    -2.09
    POSITIVE LOGITS
    ᯾
    2.25
     Mitteln
    2.20
    鸶
    2.11
    かもし
    2.06
    —”
    2.03
     trei
    1.90
    饹
    1.88
    :”
    1.88
    
    1.86
    Ꮴ
    1.85
    Activations Density 0.033%

    No Known Activations