© 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. 31-GEMMASCOPE-2-RES-16K
    7. 102
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the key content words (nouns and verbs) that carry the main ideas in formal, informational or policy‐style text.

    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
    0.61
    X
    0.54
    4
    0.54
    C
    0.50
    I
    0.49
    2
    0.49
    R
    0.49
    3
    0.48
    8
    0.48
    J
    0.47
    POSITIVE LOGITS
     sociocultural
    0.76
     infrastructural
    0.76
     intercultural
    0.73
     interdependence
    0.70
     interpersonal
    0.70
     climatic
    0.69
     alienation
    0.68
     psychosocial
    0.68
     heterogeneity
    0.67
     taxation
    0.66
    Activations Density 7.605%

    No Known Activations