© 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. 98273
    Prev
    Next
    INDEX
    Explanations

    deduct stock levels

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

    The neuron activates on terms describing the movement or subtraction of money (e.g. transfer, deduct, debited).

    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
     which
    -1.07
    teste
    -0.96
     
    -0.95
     testen
    -0.94
     that
    -0.91
    ?
    -0.88
    preis
    -0.88
    ften
    -0.87
     ألعاب
    -0.85
     À
    -0.85
    POSITIVE LOGITS
    注意事項
    1.04
    ceğiniz
    1.03
    arrivée
    0.98
    היו
    0.98
    Vendredi
    0.95
     potreb
    0.95
     nekaj
    0.94
     paff
    0.94
    깥
    0.93
    δος
    0.93
    Activations Density 0.002%

    No Known Activations