© 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. 22-GEMMASCOPE-RES-131K
    7. 12912
    Prev
    Next
    INDEX
    Explanations

    money, cost, and prices

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

    The neuron detects monetary amounts, especially dollar‐denoted prices in numeric tokens.

    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
     your
    -1.23
     traseira
    -1.09
     you
    -1.03
     другу
    -1.02
     in
    -0.96
    You
    -0.96
     where
    -0.95
    paraíso
    -0.95
    Perhaps
    -0.94
    愬
    -0.94
    POSITIVE LOGITS
    tranh
    1.30
    mbal
    1.17
     každ
    1.16
     prohib
    1.09
     addirittura
    1.09
     Mittelpunkt
    1.06
     komplett
    1.05
    badan
    1.04
    mighty
    1.02
     verschillende
    1.02
    Activations Density 0.015%

    No Known Activations