© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32153
    Prev
    Next
    INDEX
    Explanations

    publishers and editions

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

    The neuron activates on multi-digit numerical tokens that represent years or date 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
    antwoorde
    -0.78
     Devils
    -0.76
     impide
    -0.75
     conséquences
    -0.74
    ORN
    -0.71
    rzy
    -0.71
    couragement
    -0.70
     şə
    -0.70
     rẻ
    -0.70
    <0xE0>
    -0.70
    POSITIVE LOGITS
     Biomed
    0.79
    热门
    0.75
     vụ
    0.75
     chcesz
    0.73
     collection
    0.72
    食事
    0.71
     frumo
    0.71
     Teraz
    0.70
     collections
    0.70
     snad
    0.69
    Activations Density 0.008%

    No Known Activations