© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11941
    Prev
    Next
    INDEX
    Explanations

    collection operations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to programming API or data-structure method names (e.g. poll, append, remove, map, getContacts).

    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
    ictionaries
    0.63
     quadro
    0.63
    keyed
    0.63
    ompok
    0.59
    tracks
    0.59
    dicts
    0.57
     dictionaries
    0.57
    屣
    0.57
    字典
    0.56
     dictionary
    0.56
    POSITIVE LOGITS
    size
    0.67
     size
    0.64
     ruthenium
    0.55
     unle
    0.52
     coloc
    0.52
     hee
    0.52
     strontium
    0.52
     removed
    0.51
     jute
    0.51
     pon
    0.50
    Activations Density 0.004%

    No Known Activations