© 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. 11186
    Prev
    Next
    INDEX
    Explanations

    the `system` or `company`

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

    This neuron detects prominent domain-specific or formal nouns (e.g. names of statutes, acts, curricula, organizations, technical items).

    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
    Tambah
    0.81
    utilizzo
    0.78
    D
    0.75
    Nick
    0.74
    Escol
    0.73
    Entertainment
    0.73
    N
    0.73
    F
    0.72
    España
    0.71
    Un
    0.71
    POSITIVE LOGITS
     nascent
    0.88
     insofar
    0.63
     inasmuch
    0.63
     adduced
    0.60
     constituer
    0.60
     overburden
    0.58
     $_{\
    0.58
     ${
    0.57
    \*
    0.56
     incipient
    0.56
    Activations Density 0.276%

    No Known Activations