© 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. 34-GEMMASCOPE-RES-131K
    7. 32697
    Prev
    Next
    INDEX
    Explanations

    stock price movements

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

    This neuron activates on numeric and finance‐related tokens—i.e. numbers, percentages, and words tied to financial figures like stock prices, yields, or market metrics.

    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
     Buying
    -0.96
     سبب
    -0.93
    Buying
    -0.92
    nemers
    -0.85
    decoración
    -0.84
     membeli
    -0.84
    aian
    -0.84
     odkry
    -0.82
     kobieta
    -0.82
     szükség
    -0.81
    POSITIVE LOGITS
     rallied
    1.38
     rebound
    1.34
     rally
    1.20
     oscill
    1.13
     rose
    1.05
     tank
    1.05
     hit
    1.03
     rallying
    1.03
     soared
    1.03
     fell
    1.02
    Activations Density 0.026%

    No Known Activations