© 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. 86940
    Prev
    Next
    INDEX
    Explanations

    pack, package, packing

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

    The neuron activates on tokens containing the substring “pack” (e.g. pack, packed, packing, package, unpack) regardless of context.

    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
    留在
    -0.94
     contempl
    -0.92
     albeit
    -0.92
     maintenance
    -0.90
    chiato
    -0.86
    ↵↵
    -0.86
    鹇
    -0.86
     patente
    -0.85
    <em>
    -0.84
     personali
    -0.84
    POSITIVE LOGITS
    pack
    1.78
     pack
    1.70
     Pack
    1.67
    Pack
    1.43
     packing
    1.29
    PACK
    1.29
    Packs
    1.23
     lunches
    1.22
     Pak
    1.18
    packing
    1.18
    Activations Density 0.017%

    No Known Activations