© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12887
    Prev
    Next
    INDEX
    Explanations

    field specific consequences

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

    The neuron strongly activates on specialized, domain-specific technical or scientific terminology.

    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
    amiento
    0.96
    an
    0.96
    kosten
    0.91
    amines
    0.88
    amine
    0.85
    kamer
    0.84
    t
    0.83
    anego
    0.82
    ah
    0.81
    ー
    0.79
    POSITIVE LOGITS
     AcOH
    1.12
    રણ
    1.09
    AddItem
    1.01
    ן
    1.00
    na
    0.99
     JDBC
    0.97
    რ
    0.96
    Markers
    0.95
     Inhibition
    0.95
    OrElse
    0.95
    Activations Density 2.572%

    No Known Activations