© 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. 84402
    Prev
    Next
    INDEX
    Explanations

    parseInt, unsigned, UIColor, require

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

    The neuron is activated by numeric tokens—literal numbers, digit sequences, and numeric constants.

    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
    春天
    -0.94
    봄
    -0.88
     antes
    -0.88
    ḥ
    -0.86
    和
    -0.84
    arschu
    -0.81
     oglą
    -0.81
    ньше
    -0.81
     和
    -0.81
     kroner
    -0.81
    POSITIVE LOGITS
     suaminya
    1.09
     彩色
    1.03
     används
    1.01
    Suka
    1.01
     kartą
    0.99
    Dá
    0.99
    ificados
    0.98
    Referințe
    0.98
     gyvento
    0.95
     尾
    0.94
    Activations Density 0.025%

    No Known Activations