© 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. 98797
    Prev
    Next
    INDEX
    Explanations

    Hubbard model physics

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

    The neuron fires on specialized condensed-matter physics terminology (especially ferro-/ferroelectricity and related solid-state concepts).

    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
    戊
    -0.80
     Dolan
    -0.73
     HAZ
    -0.73
     chiral
    -0.73
     awoke
    -0.71
     косме
    -0.70
    CBR
    -0.70
    GetField
    -0.69
    campaign
    -0.69
     Campo
    -0.69
    POSITIVE LOGITS
     Hubbard
    1.46
    Hub
    1.17
     disproportion
    0.85
     Hub
    0.83
     Mott
    0.82
     tight
    0.81
     HUB
    0.76
    lati
    0.76
     Merino
    0.75
    太陽
    0.75
    Activations Density 0.069%

    No Known Activations