© 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. 15916
    Prev
    Next
    INDEX
    Explanations

    end of sections or options

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

    This neuron fires specifically on relatively rare, content-heavy words or acronyms (multi-syllable nouns and capitalized terms) 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
     علاقے
    0.84
     água
    0.83
    福島
    0.82
     повседнев
    0.81
     Chongqing
    0.80
     чемпиона
    0.78
     Fernanda
    0.78
    苧
    0.78
     جوئے
    0.77
    Karte
    0.77
    POSITIVE LOGITS
    optional
    0.93
     optional
    0.82
    ى
    0.79
     Ideally
    0.75
     folders
    0.74
     folder
    0.73
    approved
    0.71
     Subscribers
    0.70
    ורי
    0.70
    includes
    0.68
    Activations Density 0.001%

    No Known Activations