© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70003
    Prev
    Next
    INDEX
    Explanations

    business and property descriptions

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

    The neuron strongly activates on the legal-style modal verb “shall,” marking formal statutory or regulatory wording.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وين
    -0.89
    мый
    -0.81
    autant
    -0.80
    Trav
    -0.78
    が上が
    -0.76
    жный
    -0.75
    髒
    -0.75
    ایید
    -0.75
    zać
    -0.74
    NOST
    -0.73
    POSITIVE LOGITS
     Boulogne
    0.91
     meras
    0.86
     premises
    0.84
     knowingly
    0.83
     person
    0.82
     situs
    0.82
    getahuan
    0.81
    ẳng
    0.80
    εται
    0.79
    新浪
    0.79
    Activations Density 0.029%

    No Known Activations