© 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. 8096
    Prev
    Next
    INDEX
    Explanations

    survival, health, trade-offs

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

    This neuron flags the single most content-bearing token in a clause—i.e. the key “action” or “focus” word (verbs, gerunds, important nouns or markers like “to”) that carries the main semantic load of the phrase.

    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
    *((
    0.74
    ల్ని
    0.72
     prenatal
    0.71
     recour
    0.70
    ्योपै
    0.70
     vasena
    0.68
     superviv
    0.67
    윅
    0.66
    늉
    0.66
    ǘ
    0.65
    POSITIVE LOGITS
    ت
    0.88
    ed
    0.88
    t
    0.87
     Awakening
    0.84
     Amendments
    0.83
     Orche
    0.83
     Podcast
    0.82
     Onder
    0.82
     темы
    0.79
     Artikel
    0.78
    Activations Density 0.000%

    No Known Activations