© 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. 59137
    Prev
    Next
    INDEX
    Explanations

    year numbers or figures

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

    The neuron strongly activates on numeric tokens—especially multi‐digit numbers like years and dates.

    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
    崭
    -0.88
     vane
    -0.74
    Faça
    -0.73
    Besides
    -0.70
     作り方
    -0.69
    こんばんは
    -0.69
     withstand
    -0.69
    urada
    -0.69
    こんにちは
    -0.68
    Buenas
    -0.68
    POSITIVE LOGITS
     aku
    0.88
     acquire
    0.85
     Christianity
    0.84
     acquisition
    0.82
     Sule
    0.81
     Aqu
    0.80
    ಕ
    0.80
     République
    0.79
     acquired
    0.77
     την
    0.77
    Activations Density 0.018%

    No Known Activations