© 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. 22-GEMMASCOPE-RES-131K
    4. 10907
    Prev
    Next
    INDEX
    Explanations

    index token in code or file paths

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

    The neuron responds to occurrences of the substring “index” in identifiers or words (e.g. index, indexes, IndexVolumeWriter, indexable).

    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
    <i>
    -2.55
    …….
    -2.48
    ;
    
    -2.41
    </i>
    -2.38
    .’
    -2.34
     haupts
    -2.25
    ↵↵
    -2.23
    anthin
    -2.23
     hotly
    -2.19
     notoriously
    -2.17
    POSITIVE LOGITS
     behov
    3.23
     lyder
    2.97
     BROTHERS
    2.94
     vaksin
    2.91
     diki
    2.84
     hunde
    2.84
     DÍA
    2.83
     berge
    2.80
     disiplin
    2.75
     اذا
    2.73
    Activations Density 0.017%

    No Known Activations