© 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. 531
    Prev
    Next
    INDEX
    Explanations

    The neuron is specially tuned to detect mentions of life and living (forms of “live,” “lived,” “living,” “life,” etc.).

    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
     sobald
    0.33
     reliable
    0.31
     spoj
    0.31
     mathrm
    0.30
     appears
    0.29
    〇
    0.29
     \,
    0.29
     °
    0.28
     workpiece
    0.28
     gyak
    0.28
    POSITIVE LOGITS
     peacefully
    0.58
     awhile
    0.55
     miserably
    0.55
     miserable
    0.52
     länger
    0.51
     longer
    0.50
     länge
    0.50
     huddled
    0.49
     destitute
    0.48
    longer
    0.47
    Activations Density 0.666%

    No Known Activations