© 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. 103899
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign scripts

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

    The neuron fires on HTML numeric character‐reference sequences (e.g. “
”) that encode control characters.

    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
     Farrell
    -0.76
     IDisposable
    -0.73
     x
    -0.72
    椋
    -0.71
    pertoire
    -0.71
    洁
    -0.70
     السن
    -0.69
     sheltered
    -0.68
    liced
    -0.68
     //
    -0.67
    POSITIVE LOGITS
     bay
    0.84
     ベル
    0.81
    alog
    0.81
    oud
    0.80
    Пра
    0.80
    成员
    0.79
    étrie
    0.76
    Гар
    0.76
     viaje
    0.74
    ஒ
    0.74
    Activations Density 0.003%

    No Known Activations