© 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. 22-GEMMASCOPE-RES-131K
    7. 68998
    Prev
    Next
    INDEX
    Explanations

    scientific measurement and assessment

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

    scientific measurement terms in medical and technical research contexts.

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

    This neuron detects domain‐specific quantitative measurement or parameter terms (e.g. orientation, leakage, temperature, glucose, strain, permeability) used in technical or scientific contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     początku
    -1.57
    ꜆
    -1.45
    atization
    -1.45
    procedures
    -1.45
    practices
    -1.34
    -1.34
    atized
    -1.31
    ㆆ
    -1.29
     dismin
    -1.28
    Ꮭ
    -1.27
    POSITIVE LOGITS
     analysis
    2.28
     evaluation
    1.80
     assessment
    1.77
     information
    1.67
     study
    1.59
     data
    1.50
     and
    1.42
     analyses
    1.33
     studies
    1.33
     investigation
    1.26
    Activations Density 0.197%

    No Known Activations