© 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. 484
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on salient content words—especially nouns and verbs carrying the main semantic load of a sentence.

    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
    และ
    0.44
     ਅਤੇ
    0.44
     және
    0.44
    ：
    0.42
     แต่
    0.40
    E
    0.40
     และ
    0.39
     এবং
    0.39
     và
    0.38
    和
    0.38
    POSITIVE LOGITS
     whatnot
    0.75
     sebagainya
    0.63
     autres
    0.60
     other
    0.60
     outras
    0.57
     outros
    0.56
     tribulations
    0.54
     другие
    0.53
     andere
    0.52
     innych
    0.52
    Activations Density 1.500%

    No Known Activations