© 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. 4307
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to content‐bearing (i.e. “important”) words—non–stopwords such as key nouns, verbs, and adjectives rather than purely grammatical tokens.

    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
    1
    0.66
    2
    0.61
    6
    0.61
    0
    0.59
    4
    0.58
     solver
    0.57
    3
    0.56
     streamwise
    0.55
    7
    0.55
     collaborator
    0.54
    POSITIVE LOGITS
    各类
    0.69
    viendo
    0.68
     абсолютно
    0.68
    是非常
    0.63
    ที่เรา
    0.60
    整體
    0.60
     nuestra
    0.60
    generally
    0.60
     nuestro
    0.59
     हमारी
    0.59
    Activations Density 1.308%

    No Known Activations