© 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. 116531
    Prev
    Next
    INDEX
    Explanations

    years

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

    The neuron fires on explicit year or date mentions (for example, “by the year 2000” or similar numeric-year expressions).

    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
     při
    -0.85
     occasionally
    -0.84
     WEEKS
    -0.83
     usually
    -0.81
    گانه
    -0.80
    煸
    -0.80
    ığım
    -0.78
     della
    -0.77
    orum
    -0.77
    外的
    -0.77
    POSITIVE LOGITS
     year
    6.84
    year
    4.31
     Year
    4.22
    Year
    4.03
     año
    3.61
     YEAR
    3.56
    YEAR
    3.30
     année
    3.20
     בשנת
    3.14
     năm
    3.09
    Activations Density 0.087%

    No Known Activations