© 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. 12485
    Prev
    Next
    INDEX
    Explanations

    The neuron is strongly activated by rare or unusually long tokens (e.g. uncommon names, numbers, or infrequent word pieces).

    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
     женщины
    0.92
     мужчины
    0.89
    ucked
    0.86
     seduced
    0.83
    rolysis
    0.82
    Ꮇ
    0.81
     വൈദ്യ
    0.81
    𝐠
    0.80
    𒊹
    0.80
    𝐦
    0.80
    POSITIVE LOGITS
     Data
    0.95
     data
    0.81
     Tools
    0.80
     Analytics
    0.78
    0
    0.76
    vs
    0.75
     S
    0.75
     (
    0.75
     advancements
    0.75
     Pes
    0.75
    Activations Density 0.000%

    No Known Activations