© 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. 10-GEMMASCOPE-RES-131K
    4. 41289
    Prev
    Next
    INDEX
    Explanations

    cheese and cheeseburger related words

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

    The neuron strongly activates on mentions of cheese and cheese‐based foods (e.g. cheesecake, cheesesteaks, cheeseburgers, cream cheese).

    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
    t
    -2.52
    瑧
    -2.48
     Including
    -2.17
     Naturally
    -2.17
    翃
    -2.14
     Whether
    -2.13
     Needless
    -2.09
     Ultimately
    -2.09
     Importantly
    -2.09
     Eventually
    -2.08
    POSITIVE LOGITS
    '
    2.44
    謦
    2.30
    ῞
    2.08
     distritos
    2.00
    acterísticas
    1.98
    ſu
    1.92
    图为
    1.91
     герои
    1.81
    wonderful
    1.80
    海の
    1.77
    Activations Density 0.002%

    No Known Activations