© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103556
    Prev
    Next
    INDEX
    Explanations

    tracer arrival and pulse measurement

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

    The neuron fires on highly technical measurement‐method terms (e.g. chromatographic separation, tracer analysis, thermodilution/indicator‐dilution).

    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
     Evaporation
    -0.75
    leren
    -0.71
     evaporation
    -0.71
    Evaporation
    -0.69
    rossed
    -0.69
     terras
    -0.69
    NASA
    -0.69
     Buys
    -0.69
    찼
    -0.68
     suple
    -0.67
    POSITIVE LOGITS
     tracer
    1.46
     breakthrough
    1.17
     arrival
    1.15
     travel
    1.14
     BTC
    1.13
    BTC
    1.02
    tracer
    1.01
     tracing
    0.97
    arrival
    0.97
     fronts
    0.96
    Activations Density 0.085%

    No Known Activations