© 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. 118399
    Prev
    Next
    INDEX
    Explanations

    cell culture conditions

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

    references to cell cultures, particularly those grown in vitro or in three-dimensional environments.

    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
    MutableLiveData
    -0.80
     Sochi
    -0.76
    pean
    -0.73
    anta
    -0.73
     {?>
    -0.72
    iços
    -0.72
    IVEN
    -0.72
    urusan
    -0.72
    сток
    -0.71
    的问道
    -0.71
    POSITIVE LOGITS
     culture
    1.80
     cultures
    1.41
    culture
    1.23
     CULTURE
    1.19
     Culture
    1.16
     культуры
    1.02
    Culture
    0.99
     Cultures
    0.99
    cultures
    0.98
     conditioned
    0.94
    Activations Density 0.253%

    No Known Activations