© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129541
    Prev
    Next
    INDEX
    Explanations

    The neuron is picking out numeric tokens (numbers and related numeric-formatted strings) wherever they occur.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code, programming, and data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    為に
    -1.13
     biela
    -1.02
    を選択します
    -0.98
     उपकरण
    -0.96
     depósitos
    -0.96
    筈
    -0.95
     tocado
    -0.95
     helicópter
    -0.94
     puentes
    -0.92
    komp
    -0.91
    POSITIVE LOGITS
    woners
    0.89
    そうですが
    0.86
    そうで
    0.85
    纏
    0.84
    段时间
    0.84
    些什么
    0.83
    iam
    0.83
    ICTION
    0.82
     
    0.81
    ̓
    0.81
    Activations Density 0.006%

    No Known Activations