© 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. 13886
    Prev
    Next
    INDEX
    Explanations

    hyphenated compound nouns markdown formatting

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

    The neuron fires most strongly on content‐bearing keywords—salient nouns, verbs, dates, or other terms that signal a document’s main topic.

    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
     ’
    0.75
    locations
    0.71
     sexuales
    0.71
    ి
    0.69
     ”
    0.68
    \}=\
    0.67
    singleton
    0.67
     बर्फ
    0.66
    ➨
    0.66
    getExtension
    0.65
    POSITIVE LOGITS
    니다
    0.84
    ಶ್ರೀ
    0.79
    Ч
    0.79
    ید
    0.77
     maturing
    0.77
     réunis
    0.77
    시대
    0.76
    까지
    0.74
     AGA
    0.73
    시
    0.73
    Activations Density 0.001%

    No Known Activations