© 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. 107798
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and periods of time

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

    The neuron activates on numeric tokens and quantity expressions (e.g. numbers, years, dollar amounts, and other numeric measures).

    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
    錢
    -1.00
     хотят
    -0.84
     qualquer
    -0.84
     після
    -0.83
    ריה
    -0.81
     segurança
    -0.81
     contratar
    -0.81
    之类的
    -0.81
    的状态
    -0.79
     McP
    -0.77
    POSITIVE LOGITS
     worth
    4.25
     of
    3.72
    Worth
    2.77
    worth
    2.75
     Worth
    2.72
     WORTH
    2.23
    WORTH
    2.08
    值得
    1.66
     worthy
    1.64
    worths
    1.63
    Activations Density 0.044%

    No Known Activations