© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33996
    Prev
    Next
    INDEX
    Explanations

    programming contexts and foreign words

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

    This neuron picks out the key topic words (tags and title tokens) that appear at the start of a programming question.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    核心
    -0.87
     alko
    -0.86
     spiritu
    -0.85
    Ж
    -0.84
     ваз
    -0.84
    关于
    -0.84
    奈
    -0.82
    最近
    -0.82
    Kalau
    -0.82
     klass
    -0.81
    POSITIVE LOGITS
     <<-
    1.16
     recensione
    1.02
     pfle
    0.99
     pozor
    0.98
    assic
    0.96
     Krankenhaus
    0.95
     हूं
    0.94
    ◝
    0.94
     AppBar
    0.93
    //!
    0.91
    Activations Density 0.449%

    No Known Activations