© 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. 34-GEMMASCOPE-RES-131K
    7. 93845
    Prev
    Next
    INDEX
    Explanations

    Months and days

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

    The neuron strongly activates on numeric tokens (sequences of digits, like version numbers, dates, and other 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_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
     белье
    -0.91
    而后
    -0.91
    DEO
    -0.89
    ≲
    -0.89
    ってない
    -0.89
    HYDR
    -0.88
    合わせる
    -0.87
    
    -0.85
    adari
    -0.85
     azules
    -0.85
    POSITIVE LOGITS
    توضیحات
    1.21
     piacevole
    1.19
    According
    1.16
    Beberapa
    1.09
    Transk
    1.09
    Forrás
    1.07
    Menurut
    1.05
    Themen
    1.05
    虽然
    1.04
    lawayo
    1.03
    Activations Density 0.083%

    No Known Activations