© 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. 34-GEMMASCOPE-RES-131K
    7. 38181
    Prev
    Next
    INDEX
    Explanations

    button classes and attributes

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

    The neuron is specialized to pick out numeric literals (any standalone numbers) in code or markup.

    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
    ecie
    -0.88
     pédagog
    -0.83
    Weekend
    -0.83
    用户名
    -0.81
    AssignableFrom
    -0.79
    Rud
    -0.79
     outsourced
    -0.79
    ή
    -0.78
    📬
    -0.77
     umgekehrt
    -0.77
    POSITIVE LOGITS
     btn
    0.96
    usto
    0.86
     Tool
    0.85
    ջ
    0.83
    TRIBUN
    0.83
    tool
    0.82
    IconButton
    0.77
     tool
    0.76
    btn
    0.76
    dropdown
    0.72
    Activations Density 0.004%

    No Known Activations