© 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. 10-GEMMASCOPE-RES-131K
    7. 38858
    Prev
    Next
    INDEX
    Explanations

    real world application/concept

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

    The neuron fires on mentions of practical, real-world contexts or applications.

    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
     his
    -1.74
    馓
    -1.72
    たつ
    -1.70
    bronn
    -1.63
    たり
    -1.59
    ський
    -1.59
     journaliste
    -1.59
     don
    -1.59
     disebutkan
    -1.58
    ].
    -1.57
    POSITIVE LOGITS
     economical
    1.87
     existing
    1.87
    Y
    1.77
    鷓
    1.77
     vorhand
    1.73
    ve
    1.69
    s
    1.66
    il
    1.66
     deviations
    1.66
     powietrza
    1.65
    Activations Density 0.004%

    No Known Activations