© 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. 10-GEMMASCOPE-RES-131K
    7. 13192
    Prev
    Next
    INDEX
    Explanations

    business groups and leaders

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

    The neuron is specialized in detecting mentions of “business” (and its plural/forms) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    There
    -1.51
     leveraging
    -1.47
     infal
    -1.41
    entamiento
    -1.41
     auxiliar
    -1.39
     Seems
    -1.38
     heightened
    -1.38
    ísica
    -1.36
    They
    -1.35
     cantos
    -1.34
    POSITIVE LOGITS
    0
    1.69
     sullen
    1.66
     المختلفة
    1.52
     verschiedener
    1.51
     creat
    1.47
    ïa
    1.47
    pe
    1.45
     absurd
    1.45
    de
    1.45
     acht
    1.44
    Activations Density 0.048%

    No Known Activations