© 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. 34-GEMMASCOPE-RES-131K
    7. 65445
    Prev
    Next
    INDEX
    Explanations

    proteins, system, transport functions

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

    The neuron identifies scientific terms and concepts related to bacterial genetics, particularly focusing on protein transport, secretion systems, and bacterial cell components.

    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_34/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
    platin
    -0.85
     UTF
    -0.78
    ENTO
    -0.77
     сча
    -0.76
    lever
    -0.74
     muuta
    -0.74
     blanda
    -0.74
     семина
    -0.73
    ㄀
    -0.73
     ganado
    -0.72
    POSITIVE LOGITS
     oper
    1.08
     virulence
    0.92
    oper
    0.92
     biofilm
    0.87
     cluster
    0.87
     genes
    0.87
     Bile
    0.82
     Uptake
    0.80
     encode
    0.80
    ונ
    0.79
    Activations Density 0.185%

    No Known Activations