© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8923
    Prev
    Next
    INDEX
    Explanations

    implementation and adoption

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

    The neuron fires on formal regulatory or policy‐implementation language—terms like “compliance,” “operational,” “economic,” “phased in,” “implementation,” etc., that typically appear in documents describing rules, timelines, and stages.

    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
    فظ
    0.51
     pours
    0.50
     constantes
    0.50
     محفوظ
    0.50
    乾
    0.49
     fluids
    0.49
     отношений
    0.49
    絲
    0.48
    恋愛
    0.48
     हल्
    0.47
    POSITIVE LOGITS
     implementation
    1.95
     adoption
    1.85
    implementation
    1.81
     внед
    1.78
    Implementation
    1.77
     implementations
    1.74
     Implementation
    1.73
    adoption
    1.73
     Adoption
    1.67
     implement
    1.66
    Activations Density 0.669%

    No Known Activations