© 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. 11262
    Prev
    Next
    INDEX
    Explanations

    lists of items

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

    The neuron activates on terms naming collection or container types (e.g. array, vector, list, and similar) in code or API documentation.

    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
    輒
    -1.72
    (/^
    -1.70
    ⚣
    -1.63
    𓍊
    -1.50
    ཽ
    -1.49
    obiety
    -1.45
     observable
    -1.44
    姦
    -1.42
    freie
    -1.41
     أق
    -1.37
    POSITIVE LOGITS
    場所で
    1.54
    ÑOS
    1.47
    ляет
    1.46
     Personalis
    1.45
     similar
    1.45
     kemudian
    1.42
    ||||||||
    1.40
    琹
    1.40
    .,"
    1.38
    亊
    1.38
    Activations Density 0.037%

    No Known Activations