© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4831
    Prev
    Next
    INDEX
    Explanations

    principles

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

    The neuron fires on explicit mentions of “rule” (often numbered or named, e.g. legal rules, technical/right-hand rules, etc.).

    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_24_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
     convoc
    0.73
     editorials
    0.69
    শিদ
    0.68
     رجسٹ
    0.67
     Aye
    0.66
     edecek
    0.66
    𝙥
    0.66
     Ander
    0.65
     tasar
    0.64
    嬂
    0.64
    POSITIVE LOGITS
     법칙
    0.96
     adage
    0.90
     Principle
    0.89
    定律
    0.88
     principle
    0.86
     theorem
    0.86
     hypothesis
    0.84
     criterion
    0.82
     Theory
    0.82
    applicable
    0.80
    Activations Density 0.318%

    No Known Activations