© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14677
    Prev
    Next
    INDEX
    Explanations

    impacts

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find formal legal or contractual terminology (e.g., disclaimers, enforcement, institutional advisories).

    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
    ጧ
    0.80
    ありません
    0.79
    joyed
    0.78
     അനുവദ
    0.77
     כן
    0.76
     đừng
    0.75
     идеально
    0.75
    ﮈ
    0.75
     conhecido
    0.74
     обеспечивает
    0.73
    POSITIVE LOGITS
    pang
    0.78
     microsc
    0.75
    mdash
    0.74
     slings
    0.73
     raft
    0.72
     Bang
    0.72
    面板
    0.72
     bang
    0.70
     panels
    0.69
     blockchains
    0.69
    Activations Density 0.001%

    No Known Activations