© 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. 107664
    Prev
    Next
    INDEX
    Explanations

    linear over ranges

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

    The main thing this neuron does is find numeric measurement values (raw numbers indicating experimental data points).

    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
    いくつかの
    -0.90
    lante
    -0.85
     occasionally
    -0.82
     massima
    -0.81
     行き
    -0.77
    onekana
    -0.77
     alimentare
    -0.74
    대로
    -0.74
     asciug
    -0.73
    MBOL
    -0.72
    POSITIVE LOGITS
     over
    3.97
     throughout
    2.50
     across
    2.22
     över
    2.08
    throughout
    1.99
     between
    1.87
    across
    1.82
     down
    1.80
    over
    1.76
     yli
    1.68
    Activations Density 0.211%

    No Known Activations