© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58562
    Prev
    Next
    INDEX
    Explanations

    introductions and statements

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

    This neuron fires strongly on the infinitival “to …” purpose clauses (and their coordinating conjunctions/semicolons) that list formal objectives.

    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
     鬼
    -0.90
    Отзыв
    -0.82
     seguirá
    -0.79
     ilustraciones
    -0.77
     perdió
    -0.76
     since
    -0.75
     first
    -0.74
     sest
    -0.73
    われる
    -0.73
     five
    -0.73
    POSITIVE LOGITS
     incidental
    0.98
     любые
    0.97
    ใด
    0.95
     expedient
    0.94
    timus
    0.93
     necessary
    0.90
     tudo
    0.90
    necessary
    0.89
     anything
    0.87
     desem
    0.85
    Activations Density 0.009%

    No Known Activations