© 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. 10-GEMMASCOPE-RES-131K
    4. 110570
    Prev
    Next
    INDEX
    Explanations

    season or version numbers for media

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

    The neuron is activated by numeric tokens (especially those indicating versions, model or episode/season numbers).

    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
     for
    -3.30
     by
    -2.84
     because
    -2.70
     while
    -2.69
     and
    -2.63
     during
    -2.63
     as
    -2.55
     if
    -2.39
     from
    -2.33
     after
    -2.22
    POSITIVE LOGITS
    秾
    2.06
    罍
    1.97
    鷽
    1.94
    ཌ
    1.91
    絰
    1.84
    Ideally
    1.80
    臯
    1.78
    菒
    1.74
    
    1.73
     gouverneur
    1.73
    Activations Density 0.056%

    No Known Activations