© 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. 22-GEMMASCOPE-RES-131K
    7. 34726
    Prev
    Next
    INDEX
    Explanations

    yearly sports statistics

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

    The neuron strongly activates on numeric tokens (digits, years, stats/measurements) – i.e. it picks out numbers and numerical data.

    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
     its
    -1.55
     их
    -1.42
     their
    -1.41
     they
    -1.37
    彼らは
    -1.34
     when
    -1.18
     it
    -1.18
    双方
    -1.16
    ｃｍ
    -1.13
    頜
    -1.13
    POSITIVE LOGITS
     year
    1.27
     
    1.25
    Year
    1.21
     yearly
    1.20
     Year
    1.13
     annual
    1.09
    ปี
    1.04
     Herausforderung
    1.04
     Aufmerksamkeit
    1.04
     özellikle
    1.03
    Activations Density 0.017%

    No Known Activations