© 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. 23552
    Prev
    Next
    INDEX
    Explanations

    breath tests and measurements

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

    terminology and measurements related to breath tests or breath analysis.

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

    This neuron principally fires on quantitative data tokens—numbers, units, and measurement terms in scientific or clinical 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_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
    teins
    -0.84
     cg
    -0.83
    Stokes
    -0.81
    檐
    -0.78
    ecimento
    -0.75
    に対し
    -0.75
    Structured
    -0.73
    CIS
    -0.73
     lf
    -0.73
    fax
    -0.72
    POSITIVE LOGITS
     breath
    3.38
     Breath
    2.73
    breath
    2.56
    Breath
    2.39
     breathe
    2.00
     breaths
    1.65
     breathed
    1.53
     breat
    1.49
     blowing
    1.48
    breathe
    1.43
    Activations Density 0.048%

    No Known Activations