© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14637
    Prev
    Next
    INDEX
    Explanations

    pros and cons

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

    This neuron detects occurrences of the word “express,” as in “express or implied warranty.”

    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
     глаза
    0.74
     пройдет
    0.67
     불구하고
    0.64
    ﺮ
    0.61
     обладает
    0.60
    最具
    0.60
    ုပ်တို့
    0.59
    RA
    0.58
     продолжает
    0.58
    রকম
    0.57
    POSITIVE LOGITS
     भाज
    0.57
    zü
    0.57
     cima
    0.56
     Lalu
    0.56
     (.)
    0.54
    ları
    0.54
     funcionarios
    0.54
    redux
    0.53
    vex
    0.53
     aliphatic
    0.53
    Activations Density 0.000%

    No Known Activations