© 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. 33510
    Prev
    Next
    INDEX
    Explanations

    prices and costs

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

    This neuron detects numeric tokens, especially digits in price or monetary amounts.

    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
     and
    -1.09
     ternura
    -1.05
     Umfeld
    -1.01
    状態で
    -0.99
     若い
    -0.98
     the
    -0.95
    Trả
    -0.94
    感じで
    -0.93
    picasso
    -0.93
     Kích
    -0.91
    POSITIVE LOGITS
    0
    1.19
     COMPOUNDS
    1.15
     aikana
    1.00
     käyttö
    0.96
     onsdag
    0.95
     ané
    0.95
    душка
    0.93
    🕋
    0.93
     ister
    0.93
     dollars
    0.91
    Activations Density 0.026%

    No Known Activations