© 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. 10-GEMMASCOPE-RES-131K
    4. 71214
    Prev
    Next
    INDEX
    Explanations

    years and dates

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

    The neuron fires on four-digit year numbers (i.e. references to dates like “1999,” “2000,” “2021,” etc.).

    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
     pouvons
    -1.59
     subió
    -1.55
     but
    -1.51
    紧紧
    -1.49
    loride
    -1.45
    ólicas
    -1.43
    rrrr
    -1.43
    CLAIMER
    -1.42
    BeNil
    -1.40
    MessageOf
    -1.39
    POSITIVE LOGITS
     by
    2.05
     it
    1.84
     your
    1.60
    〜。
    1.55
     varandra
    1.45
     gustar
    1.42
     about
    1.41
     like
    1.35
    selben
    1.35
     事例
    1.32
    Activations Density 0.056%

    No Known Activations