© 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. 12185
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on content-bearing (especially technical or domain-specific) words 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
     этих
    0.79
    これらの
    0.77
     primeiras
    0.74
     نخست
    0.73
     radiolysis
    0.72
     těchto
    0.72
     második
    0.70
    ༔
    0.70
    ucidation
    0.69
     setelah
    0.69
    POSITIVE LOGITS
     someone
    0.67
     Michelle
    0.67
     Studio
    0.65
     onscreen
    0.64
    ва
    0.63
     personnelle
    0.63
    rollen
    0.63
     UConn
    0.63
     Clemson
    0.62
     chatt
    0.62
    Activations Density 0.000%

    No Known Activations