© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 9719
    Prev
    Next
    INDEX
    Explanations

    science and scientists

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

    The neuron fires strongly on the core “thesis” clauses or pivotal statements of a passage—i.e. when the text presents its main conclusion or key factual claim.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    contrasting statements or turning points introduced by coordinating conjunctions like "but."

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     unapolog
    0.87
     omnichannel
    0.80
     headcount
    0.80
     uptick
    0.79
     amplio
    0.78
     subsum
    0.78
     Downtown
    0.77
     onboarding
    0.77
    itlement
    0.77
     rebranded
    0.77
    POSITIVE LOGITS
     scientists
    1.28
     과학
    1.27
     বিজ্ঞানীরা
    1.23
    科学家
    1.21
    科學
    1.16
     वैज्ञानिकों
    1.13
    Scientists
    1.12
     விஞ்ஞான
    1.09
     العلماء
    1.09
     amazed
    1.05
    Activations Density 0.031%

    No Known Activations