© 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. 7758
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on standout content words—especially proper names or technical/jargon terms—rather than 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
    鳥
    0.77
    ="(
    0.70
    它
    0.68
    ILLE
    0.64
    핵
    0.64
    ness
    0.63
    স্
    0.63
    opharm
    0.63
     sce
    0.63
    iyi
    0.63
    POSITIVE LOGITS
    дования
    0.80
    回应
    0.80
    ங்கிணை
    0.79
     Guzman
    0.77
    龧
    0.77
    lebnis
    0.76
     свидетель
    0.76
    ेशंस
    0.75
    ون
    0.75
    动的
    0.75
    Activations Density 0.001%

    No Known Activations