© 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. 34-GEMMASCOPE-RES-131K
    7. 93358
    Prev
    Next
    INDEX
    Explanations

    chemical content proportions

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

    numerical measurements related to chemical compositions or concentrations in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric measurements and quantitative data (numbers, percentages, units) in technical or scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    unea
    -0.86
     Fläche
    -0.82
     ComVisible
    -0.80
    OfYear
    -0.79
    bánh
    -0.79
    ]='
    -0.77
     Größen
    -0.75
     CGSize
    -0.75
    eria
    -0.75
    ]!='
    -0.75
    POSITIVE LOGITS
     content
    4.78
    content
    3.66
     Content
    3.17
    Content
    3.13
    含量
    2.95
     contents
    2.88
    CONTENT
    2.80
     contenido
    2.77
     CONTENT
    2.67
     содержание
    2.52
    Activations Density 0.126%

    No Known Activations