© 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. 80
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on high-frequency English function words (common prepositions, articles, and conjunctions).

    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
    0.47
    2
    0.44
    8
    0.43
     
    0.40
    6
    0.38
    3
    0.38
    4
    0.37
    7
    0.37
    9
    0.37
     two
    0.36
    POSITIVE LOGITS
    <unused299>
    0.46
    <unused1741>
    0.46
    <unused717>
    0.46
    <unused292>
    0.45
    <unused346>
    0.44
    <unused1666>
    0.42
    <unused1757>
    0.42
     funcionalidad
    0.42
    <unused642>
    0.42
     personalizar
    0.41
    Activations Density 2.014%

    No Known Activations