© 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. 11880
    Prev
    Next
    INDEX
    Explanations

    Here's my best guess based on the provided lists:first, short, giant, plausible, ambition, beings, warehousing

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

    This neuron fires on the document’s key content words (informationally rich nouns, verbs, adjectives/adverbs) rather than on common function words.

    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
    ۞
    0.84
    ಇದ
    0.74
    㭂
    0.74
     ผม
    0.73
    まぁ
    0.72
     এছাড়াও
    0.72
    ayısıyla
    0.71
    }]}\
    0.71
    ॓
    0.71
    ﮯ
    0.70
    POSITIVE LOGITS
     Jian
    0.87
     Vander
    0.83
    ↵
    0.82
     Barrio
    0.81
    TRAN
    0.79
     Nancy
    0.77
     gráfico
    0.77
     Pilar
    0.77
     Walling
    0.76
    erti
    0.75
    Activations Density 0.000%

    No Known Activations