© 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. 61390
    Prev
    Next
    INDEX
    Explanations

    1970s and 1980s

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

    The neuron is tuned to detect numeric tokens—especially years or other numbers—wherever digits appear in the text.

    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
    ve
    -1.70
     amables
    -1.57
     العالمية
    -1.56
     milion
    -1.55
    ?»
    -1.55
    eres
    -1.55
    葙
    -1.52
     versions
    -1.50
    ล้ว
    -1.49
    ,»
    -1.49
    POSITIVE LOGITS
    “
    1.71
     også
    1.69
    很多
    1.64
     mortos
    1.62
    很多人
    1.58
     has
    1.49
     упаковки
    1.48
     Also
    1.43
    </tr>
    1.42
    잦
    1.42
    Activations Density 0.027%

    No Known Activations