© 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. 104583
    Prev
    Next
    INDEX
    Explanations

    mathematical subtraction and results

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

    The neuron is detecting subtraction operations (words like “subtract,” “subtraction,” and similar minus-related terms).

    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
     terão
    -1.02
    サンプル
    -1.02
     Pieter
    -0.99
     Formato
    -0.98
    不变
    -0.96
     Ślą
    -0.94
    uestran
    -0.94
    fixing
    -0.94
     Trotz
    -0.92
     збіль
    -0.91
    POSITIVE LOGITS
    URR
    1.12
     pensent
    0.95
    ждают
    0.94
     (-)
    0.90
    ToReturn
    0.89
    optarg
    0.88
     perdre
    0.88
     toepassing
    0.87
     faldas
    0.85
     aanzien
    0.85
    Activations Density 0.041%

    No Known Activations