© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14898
    Prev
    Next
    INDEX
    Explanations

    academic disciplines

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

    The neuron fires on occurrences of academic or scientific discipline names (e.g. “algebra,” “ecology,” “psychology,” “mechanics,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     different
    -1.45
     EVERY
    -1.18
    計畫
    -1.17
    おわりに
    -1.15
     млн
    -1.15
     six
    -1.15
     gets
    -1.13
    ೬
    -1.12
     getType
    -1.09
     troubling
    -1.09
    POSITIVE LOGITS
    specifically
    1.33
    檻
    1.30
     faciliter
    1.28
    และ
    1.26
    もあって
    1.25
    despite
    1.24
     iluminação
    1.22
     conster
    1.20
    basically
    1.19
    茈
    1.19
    Activations Density 0.116%

    No Known Activations