© 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. 68
    Prev
    Next
    INDEX
    Explanations

    of/de followed by specifying noun

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

    This neuron detects mentions of formal organizations or institutional names (e.g., “Society,” “Academy,” “Association,” “Church,” etc.).

    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
    ies
    0.22
    iv
    0.22
    y
    0.22
    en
    0.22
    ht
    0.22
    out
    0.22
    own
    0.22
    ading
    0.21
    ן
    0.21
    ian
    0.21
    POSITIVE LOGITS
     kawaida
    0.29
     rozwoju
    0.26
     ambayo
    0.26
     cristianos
    0.25
     desarrollo
    0.25
     Lanier
    0.24
     Wissenschaften
    0.24
     guerra
    0.24
     Servicios
    0.24
     Car
    0.23
    Activations Density 0.821%

    No Known Activations