© 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. 34-GEMMASCOPE-RES-131K
    4. 58842
    Prev
    Next
    INDEX
    Explanations

    Chihiro Shindō

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

    This neuron responds to numeric digit tokens, especially those comprising years or 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
    針對
    -0.79
     Noire
    -0.77
     Shakira
    -0.75
     noir
    -0.75
    abaret
    -0.74
     リビング
    -0.73
    camino
    -0.73
    蒟
    -0.73
    我就是
    -0.73
     Leggings
    -0.73
    POSITIVE LOGITS
     romantic
    1.03
    іод
    0.84
     romance
    0.79
     leukemia
    0.78
    inazione
    0.77
     rom
    0.75
    edere
    0.74
     romanti
    0.73
    inkai
    0.72
    RECORD
    0.71
    Activations Density 0.020%

    No Known Activations