© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86294
    Prev
    Next
    INDEX
    Explanations

    year by year

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

    The neuron strongly activates on the word “year,” i.e. tokens marking annual or “year”-related mentions.

    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
     of
    -2.61
     for
    -2.58
     truly
    -2.36
     which
    -2.11
     and
    -2.09
     essentially
    -2.05
     from
    -2.05
     was
    -2.02
     having
    -1.97
     that
    -1.96
    POSITIVE LOGITS
    𓁹
    2.05
    ౬
    2.02
    ఽ
    1.98
    🫃
    1.95
     astonishing
    1.88
    戋
    1.88
     diversos
    1.85
     anunció
    1.85
     ridiculously
    1.84
     ۸
    1.83
    Activations Density 0.059%

    No Known Activations