© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41158
    Prev
    Next
    INDEX
    Explanations

    biofilm formation and characteristics

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

    This neuron detects the term "biofilm" and related words like "film" in scientific texts about bacterial or microbial growth on surfaces.

    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
     to
    -2.08
     but
    -2.00
    
    -1.96
     или
    -1.83
     Then
    -1.83
     While
    -1.70
     However
    -1.70
    ist
    -1.67
     یون
    -1.67
     prioriti
    -1.65
    POSITIVE LOGITS
    '
    2.00
    
    1.93
     để
    1.93
     untuk
    1.91
    鈊
    1.83
    𓐍
    1.80
    瓛
    1.78
    内的
    1.77
    llavero
    1.77
    我们就
    1.73
    Activations Density 0.034%

    No Known Activations