© 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. 101997
    Prev
    Next
    INDEX
    Explanations

    GUI layout managers and proper nouns

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

    This neuron activates on tokens containing uppercase letters (e.g. class names, constants, or acronyms).

    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
    r
    -2.22
    AT
    -1.95
    th
    -1.92
    ta
    -1.89
    ti
    -1.88
    IN
    -1.87
    AD
    -1.82
    on
    -1.81
    容易
    -1.80
    ！」
    -1.79
    POSITIVE LOGITS
    鸶
    2.72
     laquelle
    2.20
    帔
    2.17
    BorderLayout
    2.06
    ayaquil
    2.03
    olism
    2.03
    進去
    2.02
     ſhe
    1.97
    ية
    1.96
    eleste
    1.94
    Activations Density 0.001%

    No Known Activations