© 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. 80700
    Prev
    Next
    INDEX
    Explanations

    NF-kappaB and measurement units

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

    scientific units of measurement, particularly in contexts involving temperature (degrees C), weights (microgram), and chemical notations.

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

    The neuron fires on numeric measurement expressions—numbers (and associated symbols like “±”) often paired with units (e.g. “degrees,” “micrograms”).

    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
     Wartawan
    -0.80
    Efter
    -0.78
     Drogen
    -0.75
    GroupLayout
    -0.74
    Ви
    -0.74
    ・
    -0.73
     others
    -0.73
     Quinta
    -0.73
     also
    -0.71
     really
    -0.70
    POSITIVE LOGITS
     basan
    0.82
     تعداد
    0.82
    Tratamiento
    0.80
     drenaje
    0.79
     sobran
    0.78
    大好きです
    0.78
    entary
    0.78
    …]
    0.77
     problemen
    0.77
    揪
    0.77
    Activations Density 0.164%

    No Known Activations