© 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. 75526
    Prev
    Next
    INDEX
    Explanations

    lightning strikes

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

    The neuron fires on numeric tokens and measurement‐style expressions (i.e. numbers, units, and related technical quantities).

    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
     Berwick
    -0.77
    aby
    -0.77
     Ony
    -0.76
     بف
    -0.75
    槲
    -0.74
     transgression
    -0.72
    Aby
    -0.71
    вань
    -0.71
    Partici
    -0.71
     операции
    -0.70
    POSITIVE LOGITS
     lightning
    2.20
     Lightning
    1.79
    lightning
    1.77
    Lightning
    1.77
    雷
    0.92
     Tampa
    0.87
     мол
    0.85
     lightening
    0.85
     thunder
    0.84
     victims
    0.83
    Activations Density 0.023%

    No Known Activations