© 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. 31624
    Prev
    Next
    INDEX
    Explanations

    creative movement class

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

    The neuron fires on passages announcing and describing scheduled events or classes—especially those listing activities, subjects (like music, dance, science), and timing details.

    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
    student
    -0.93
    beke
    -0.91
    Student
    -0.86
    students
    -0.83
    学生
    -0.83
     teenager
    -0.82
     teenagers
    -0.82
     sexy
    -0.81
     kHz
    -0.77
     STUDENT
    -0.77
    POSITIVE LOGITS
     puppet
    1.11
     activities
    1.10
     songs
    1.08
     families
    1.07
     play
    1.03
     imagination
    1.03
     playtime
    1.03
     parachute
    0.99
     Imagination
    0.99
    月号
    0.96
    Activations Density 0.026%

    No Known Activations