© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23676
    Prev
    Next
    INDEX
    Explanations

    mapping data or concepts

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

    The neuron fires on occurrences of the word “mapping” (and its morphological variants like “mapped,” “maps,” etc.).

    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
     Día
    -0.94
    
    -0.91
    jml
    -0.91
    HOU
    -0.90
    Prerequisites
    -0.88
     actrice
    -0.87
    狨
    -0.84
     marché
    -0.84
    읗
    -0.83
    cups
    -0.82
    POSITIVE LOGITS
     mapping
    2.30
    mapping
    2.03
     Mapping
    1.97
     onto
    1.80
    Mapping
    1.73
     mapped
    1.70
    mapped
    1.57
     mappings
    1.56
     mapper
    1.56
    mappings
    1.49
    Activations Density 0.030%

    No Known Activations