© 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. 10922
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers

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

    The neuron responds strongly to content-bearing, topic-specific words (especially proper names, brands, and key domain terms).

    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
    Becoming
    0.63
    ಯ
    0.58
    Everyone
    0.57
    нето
    0.56
    Nib
    0.55
     બન
    0.55
    $('
    0.54
    你可以
    0.54
    Totally
    0.53
    誰も
    0.52
    POSITIVE LOGITS
     some
    1.44
     an
    1.38
     a
    1.32
     something
    1.20
    some
    1.13
     einige
    1.13
     nogle
    1.13
     alcune
    1.12
     einen
    1.08
     alguns
    1.08
    Activations Density 0.558%

    No Known Activations