© 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. 34-GEMMASCOPE-RES-131K
    7. 92366
    Prev
    Next
    INDEX
    Explanations

    units of measurement

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

    The neuron selectively activates on numeric tokens that appear in measurement contexts (e.g. elevations, distances, lengths).

    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
     fantasi
    -0.94
    ру
    -0.93
    
    -0.87
     Antrag
    -0.86
     тоже
    -0.86
     misst
    -0.85
     ווע
    -0.85
     nosi
    -0.84
     भी
    -0.84
    archical
    -0.84
    POSITIVE LOGITS
     [])
    1.16
    formazioni
    0.98
     if
    0.94
    change
    0.93
     ibunya
    0.91
    strictEqual
    0.90
    してみると
    0.90
    empêcher
    0.90
     "")
    0.90
    ÁG
    0.90
    Activations Density 0.031%

    No Known Activations