© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75705
    Prev
    Next
    INDEX
    Explanations

    artistic music medical director

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

    The neuron fires on mentions of “director” in professional titles (e.g. artistic director, creative director, music director).

    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
     were
    -2.11
     the
    -1.66
    pherds
    -1.59
     hablan
    -1.56
     riguard
    -1.53
    торая
    -1.51
     to
    -1.48
     umgeben
    -1.46
    ssic
    -1.45
     вторая
    -1.41
    POSITIVE LOGITS
     Seigneur
    1.48
    {
    1.46
     jolie
    1.38
     expliqué
    1.33
     火锅
    1.32
     Mère
    1.30
    蛧
    1.30
     legyen
    1.30
    这个
    1.28
     aile
    1.28
    Activations Density 0.014%

    No Known Activations