© 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. 31-GEMMASCOPE-2-RES-16K
    7. 106
    Prev
    Next
    INDEX
    Explanations

    The neuron flags individual list items—i.e. nouns or noun phrases that appear as entries in enumerations.

    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_31_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
    の
    0.31
    ের
    0.29
    Horizontal
    0.28
     External
    0.27
    <()>
    0.27
    Ch
    0.26
    Phi
    0.26
    (([
    0.26
     Mechanisms
    0.25
    Trace
    0.25
    POSITIVE LOGITS
     etc
    0.65
    etc
    0.53
    甚至是
    0.53
     тощо
    0.51
     voire
    0.49
     etcétera
    0.48
     enfim
    0.46
    等等
    0.46
     bahkan
    0.46
     gyms
    0.46
    Activations Density 1.042%

    No Known Activations