© 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. 10-GEMMASCOPE-RES-131K
    7. 84981
    Prev
    Next
    INDEX
    Explanations

    prior-year figures, comparable validity

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

    The neuron activates on numeric and quantitative tokens—years, figures, percentages, dates, and other number-based 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_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
     will
    -1.59
    usercontent
    -1.20
    houn
    -1.19
    phate
    -1.14
    after
    -1.14
    namon
    -1.06
    arci
    -1.05
    ,
    -1.05
    Each
    -1.05
    nicas
    -1.04
    POSITIVE LOGITS
    "",
    1.27
    一个小
    1.20
    ხ
    1.19
     emphas
    1.16
    ANNES
    1.13
    应当
    1.10
     they
    1.09
     Their
    1.05
     powinny
    1.05
     their
    1.05
    Activations Density 0.025%

    No Known Activations