© 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. 73819
    Prev
    Next
    INDEX
    Explanations

    adenovirus and viruses

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

    The neuron identifies virus terminology, particularly "adenovirus" and related viral terms.

    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
    洇
    -1.67
     utilizz
    -1.67
    geſ
    -1.66
    sepeda
    -1.64
    
    -1.63
     pezzo
    -1.59
     】
    -1.56
     habido
    -1.55
     ofreci
    -1.55
     Ontology
    -1.55
    POSITIVE LOGITS
    7
    1.96
    _
    1.80
    9
    1.77
    5
    1.74
    6
    1.69
    2
    1.66
     our
    1.60
     stuffy
    1.60
     Placing
    1.59
    s
    1.59
    Activations Density 0.074%

    No Known Activations