© 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. 10-GEMMASCOPE-RES-131K
    7. 86824
    Prev
    Next
    INDEX
    Explanations

    cost and related concepts

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

    The main thing this neuron does is detect cost-related terms and expressions (e.g., cost, low-cost, cost-effective).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     that
    -1.73
     enfati
    -1.67
     apparaît
    -1.65
    
    -1.54
     verschillende
    -1.52
     impover
    -1.52
    inosaur
    -1.50
    がたくさん
    -1.49
     their
    -1.48
    problema
    -1.48
    POSITIVE LOGITS
     and
    2.27
    ------
    1.51
     &
    1.50
    ----
    1.49
    -------
    1.48
    p
    1.48
     is
    1.45
     -
    1.43
    1
    1.40
    ↵↵
    1.38
    Activations Density 0.050%

    No Known Activations