© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44022
    Prev
    Next
    INDEX
    Explanations

    years

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

    The neuron strongly activates on numeric tokens that make up dates—especially four‐digit year 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
     Lakukan
    -1.92
     Pastikan
    -1.73
     Gunakan
    -1.59
     μὲν
    -1.59
    我已经
    -1.52
    ⦑
    -1.52
     ngừa
    -1.50
     significados
    -1.49
     vývoj
    -1.48
     Saltar
    -1.45
    POSITIVE LOGITS
    in
    2.23
    0
    1.74
    R
    1.52
    A
    1.52
    L
    1.48
    os
    1.39
    ↵
    1.34
    V
    1.34
    S
    1.34
    t
    1.31
    Activations Density 0.051%

    No Known Activations