© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11452
    Prev
    Next
    INDEX
    Explanations

    training process, attention

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

    The neuron fires on mentions of organized initiatives or support efforts—words like project, program, grant, sponsorship, festival, etc.

    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
    ورسٹی
    0.70
     Thats
    0.69
     Them
    0.68
    ও
    0.66
    '/>
    0.65
     sogenannten
    0.65
    ꒪
    0.64
    Reality
    0.63
    ভার
    0.63
    ọa
    0.63
    POSITIVE LOGITS
     with
    0.77
     могут
    0.70
     avec
    0.66
     с
    0.66
     associating
    0.64
     daher
    0.63
     имеют
    0.63
     sieve
    0.62
     должны
    0.62
     dgn
    0.62
    Activations Density 1.451%

    No Known Activations