© 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. 12129
    Prev
    Next
    INDEX
    Explanations

    ages and titles

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

    The neuron specializes in spotting standalone numeric tokens (numbers, dates, ages, etc.) 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
     или
    -1.62
     anledning
    -1.55
    pulseira
    -1.48
     detaljer
    -1.43
    或者
    -1.43
     یا
    -1.41
     SEÑ
    -1.40
     ataupun
    -1.35
    鐃
    -1.34
     diferenças
    -1.33
    POSITIVE LOGITS
     was
    1.71
     been
    1.67
     souvent
    1.51
    躄
    1.44
     always
    1.43
    睹
    1.41
     nuestro
    1.38
     of
    1.38
     found
    1.36
    ⏑
    1.33
    Activations Density 0.054%

    No Known Activations