© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105312
    Prev
    Next
    INDEX
    Explanations

    food items or descriptive words

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

    The main thing this neuron does is detect mentions of flatbread‐style foods (wraps, tortillas, roti/paranthas, 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_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
    orail
    -2.11
     decisões
    -2.09
    騖
    -2.06
    </td>
    -2.05
    полне
    -2.03
     tarefas
    -1.99
    ឵
    -1.98
    vignon
    -1.97
     esboço
    -1.95
    瓩
    -1.95
    POSITIVE LOGITS
    捽
    1.88
     citing
    1.82
    ка
    1.81
    ;
    1.81
    '
    1.79
    ј
    1.77
    鍆
    1.71
     compan
    1.71
     …
    1.66
    我和
    1.65
    Activations Density 0.001%

    No Known Activations