© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66813
    Prev
    Next
    INDEX
    Explanations

    units and quantities

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

    The neuron activates on numeric measurements paired with scientific or engineering unit abbreviations (e.g. M, pc, bp, Mt, etc.), i.e. large‐scale quantitative values with units.

    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
     intric
    -1.80
    ↵↵
    -1.78
     ferv
    -1.66
    setViewName
    -1.66
     erhältlich
    -1.65
    ⚋
    -1.63
     respostas
    -1.55
    decoración
    -1.55
    uesday
    -1.53
    麁
    -1.52
    POSITIVE LOGITS
    Following
    1.97
     ткани
    1.91
    While
    1.75
    さてさて
    1.74
    Shortly
    1.73
    Aside
    1.73
    Having
    1.71
     cedera
    1.70
    Ironically
    1.70
     besar
    1.68
    Activations Density 0.020%

    No Known Activations