© 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. 9563
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

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

    This neuron fires strongly on the very first substantive token (the "lead" word) of each text snippet, effectively marking the opening content word of each document segment.

    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
    춧
    0.90
    ರ್‌
    0.89
    ляць
    0.88
    베이스
    0.84
    áver
    0.84
     знает
    0.81
    дьми
    0.80
     glaucoma
    0.80
    льбе
    0.80
     казіно
    0.79
    POSITIVE LOGITS
    ↵
    0.84
     excited
    0.78
     Apartment
    0.77
     u
    0.76
    z
    0.76
     Cooking
    0.74
     z
    0.73
    م
    0.72
    D
    0.72
     Employment
    0.71
    Activations Density 0.000%

    No Known Activations