© 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. 14053
    Prev
    Next
    INDEX
    Explanations

    processes and traditions

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

    The neuron fires on semantically important content words (i.e. key nouns, adjectives, and verbs) rather than on common function 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
    ﺒ
    0.82
    ﺠ
    0.78
     partire
    0.77
     উঠল
    0.76
     этап
    0.76
    лася
    0.75
    immon
    0.75
     DMBT
    0.75
    ﻤ
    0.73
    ধর্ম
    0.73
    POSITIVE LOGITS
     Area
    0.82
     Articles
    0.77
     Areas
    0.71
     kilow
    0.70
     Joanna
    0.67
     Advertise
    0.67
     Sarm
    0.66
    委員
    0.65
     Manit
    0.64
     elevators
    0.64
    Activations Density 0.001%

    No Known Activations