© 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. 15976
    Prev
    Next
    INDEX
    Explanations

    formal to casual spectrum

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

    The neuron fires on low‐frequency or specialized tokens—proper names, acronyms, numbers, and other rare or domain-specific words.

    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
     табле
    0.71
     буквально
    0.69
     눈
    0.68
     Надо
    0.66
     αὐ
    0.65
     այդ
    0.65
     Reasoning
    0.64
     জাতিসঙ্ঘ
    0.64
    ט
    0.64
    antad
    0.64
    POSITIVE LOGITS
     mover
    0.70
     reprieve
    0.69
     valet
    0.67
     commuter
    0.66
     albeit
    0.63
     occasional
    0.62
     demander
    0.61
    Agenda
    0.61
    exists
    0.61
     occasionally
    0.61
    Activations Density 1.388%

    No Known Activations