© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8251
    Prev
    Next
    INDEX
    Explanations

    specific conditions or requirements

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

    The neuron fires strongly on formal numeric or quantitative specification tokens—things like section labels, percentages, numbers, and legal‐style “if/then” condition clauses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anthem
    0.50
    ائرة
    0.49
    乀
    0.48
     apreci
    0.48
     chỉnh
    0.47
     맡
    0.47
     scooped
    0.47
    
    0.47
    ₕ
    0.47
     applaud
    0.47
    POSITIVE LOGITS
     requirements
    2.94
     Requirements
    2.78
    requirements
    2.78
     requirement
    2.73
    Requirements
    2.67
     requisitos
    2.58
    requirement
    2.58
     REQUIREMENTS
    2.55
     Requirement
    2.48
    Requirement
    2.45
    Activations Density 0.608%

    No Known Activations