© 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. 8305
    Prev
    Next
    INDEX
    Explanations

    English words starting with 'e'

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

    The neuron is keyed to technical measurement and comparison language—spots words used in describing quantitative procedures or overlaps (e.g. comparing, measure, degree, error, overlap).

    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
    <unused2156>
    0.87
    <unused2123>
    0.77
     သ
    0.70
    <unused2128>
    0.68
     zaji
    0.64
    ظام
    0.63
    忪
    0.63
    哃
    0.61
    納期
    0.61
    高于
    0.60
    POSITIVE LOGITS
     евре
    0.88
     एक्ट्रेस
    0.79
     Everglades
    0.76
     eher
    0.76
     еже
    0.75
     empezar
    0.73
     естественно
    0.73
     escrever
    0.73
     elenco
    0.73
     एवं
    0.72
    Activations Density 2.374%

    No Known Activations