© 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. 22-GEMMASCOPE-RES-131K
    7. 73248
    Prev
    Next
    INDEX
    Explanations

    years and calendar year

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

    The neuron is triggered by references to calendar years (the word “Year” and its associated numeric values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    䊏
    -2.58
    
    -2.56
    泚
    -2.36
    䊐
    -2.36
     compels
    -2.33
    🫅
    -2.33
     Zwecke
    -2.28
    矬
    -2.27
    苙
    -2.27
    があります
    -2.25
    POSITIVE LOGITS
    h
    3.28
    The
    3.09
    le
    2.89
    You
    2.69
    ve
    2.69
    A
    2.66
    li
    2.63
     Their
    2.58
    It
    2.48
    多
    2.45
    Activations Density 0.099%

    No Known Activations