© 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-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196794
    Prev
    Next
    INDEX
    Explanations

    **The neuron activates on sequences starting with "should" followed by a verb.**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ຄວ
    0.41
     متحد
    0.41
    ٫
    0.40
    miktar
    0.39
    žić
    0.38
    ሒ
    0.38
    🇾
    0.38
     لیاقت
    0.38
    សារ
    0.37
    attiyam
    0.37
    POSITIVE LOGITS
    utel
    0.41
     également
    0.40
     gastro
    0.39
     softens
    0.37
     素
    0.37
     Gast
    0.35
     sním
    0.35
     Características
    0.35
     be
    0.34
    orem
    0.34
    Activations Density 0.010%

    No Known Activations