© 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. 10-GEMMASCOPE-RES-131K
    7. 39398
    Prev
    Next
    INDEX
    Explanations

    size and frequency extent

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

    The neuron flags numeric tokens that represent quantitative measurements (especially sizes or dimensions, often in decimal form).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    If
    -1.59
    좇
    -1.59
     dazzling
    -1.59
    精美
    -1.55
    Usually
    -1.52
    唯美
    -1.52
    公式サイト
    -1.50
    引用元
    -1.48
    Sometimes
    -1.47
    </i>
    -1.45
    POSITIVE LOGITS
     and
    1.78
     alcuni
    1.75
     The
    1.70
     esimerkiksi
    1.65
    roughly
    1.63
     again
    1.62
     the
    1.60
    specifically
    1.60
     such
    1.55
     ''
    1.55
    Activations Density 0.018%

    No Known Activations