© 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. 31-GEMMASCOPE-2-RES-16K
    4. 281
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on long, multi‐syllabic, domain-specific terms—especially technical or jargon‐heavy nouns.

    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_31_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
    get
    0.54
    name
    0.48
    _
    0.48
    x
    0.45
    delete
    0.44
    id
    0.42
    は
    0.41
    q
    0.41
    z
    0.41
    Você
    0.40
    POSITIVE LOGITS
     Additionally
    1.23
     Furthermore
    1.05
     These
    0.96
     Moreover
    0.96
     Ultimately
    0.88
     Also
    0.86
     Daarnaast
    0.86
     Examples
    0.85
     Zusätzlich
    0.85
     Additional
    0.85
    Activations Density 2.014%

    No Known Activations