© 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. 76495
    Prev
    Next
    INDEX
    Explanations

    year yields

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

    The neuron strongly activates on multi‐token numeric expressions—especially hyphenated numbers paired with units (e.g. “10-year”)—as used in financial or economic 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_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
     llantas
    -0.77
    Blanc
    -0.75
    replaceable
    -0.74
    bilità
    -0.72
    adecimal
    -0.72
    Advertisements
    -0.72
    posa
    -0.72
     pained
    -0.71
    ologi
    -0.71
    充分
    -0.71
    POSITIVE LOGITS
     yield
    2.31
     yields
    2.11
    yield
    1.94
     Yield
    1.90
     Yields
    1.80
    Yield
    1.80
    yields
    1.55
     ten
    1.21
     Ten
    1.13
     yielded
    1.11
    Activations Density 0.010%

    No Known Activations