© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12855
    Prev
    Next
    INDEX
    Explanations

    name, making plans

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

    The neuron is keyed to inflectional verb suffixes (e.g. tokens ending in –ed, –ing, or –s) that mark common verb forms.

    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
     menopause
    0.80
    ﻊ
    0.78
     軽量
    0.75
     posebno
    0.75
    𝗛
    0.75
     wied
    0.73
    }\,\
    0.73
     flirting
    0.73
    𝗙
    0.71
     Wied
    0.71
    POSITIVE LOGITS
    ंना
    0.89
    datasource
    0.88
    geojson
    0.88
     sudd
    0.80
    flatMap
    0.79
    bootstrapcdn
    0.77
    서
    0.77
     maksud
    0.75
    班牙
    0.74
    configs
    0.73
    Activations Density 0.003%

    No Known Activations