© 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. 22-GEMMASCOPE-RES-131K
    7. 66639
    Prev
    Next
    INDEX
    Explanations

    programming code and legal text

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

    This neuron is triggered by numeric literals—especially multi‐digit numbers—in the text.

    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
    Rather
    -0.93
    ordnet
    -0.88
     Rather
    -0.88
     orsz
    -0.87
     hundert
    -0.85
    avond
    -0.84
     about
    -0.84
    coroutine
    -0.83
    tä
    -0.83
     DVD
    -0.82
    POSITIVE LOGITS
     planification
    1.05
     then
    0.98
     densité
    0.96
     eventually
    0.93
    Якщо
    0.92
    %);
    0.88
     結果
    0.83
     ボタン
    0.83
     addObject
    0.82
    وة
    0.82
    Activations Density 0.001%

    No Known Activations