© 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. 22-GEMMASCOPE-RES-131K
    7. 399
    Prev
    Next
    INDEX
    Explanations

    biographical descriptions of men

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

    The neuron strongly activates on occupational or role‐label words—especially musical professions (e.g. singer, songwriter, band, director)—in biographical 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_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
    ⅛
    -1.45
     if
    -1.28
     мои
    -1.25
     how
    -1.22
     pensar
    -1.22
     then
    -1.20
     when
    -1.20
     defekt
    -1.18
    × 
    -1.18
     it
    -1.17
    POSITIVE LOGITS
    zaron
    1.41
     TÉCNICA
    1.41
     coque
    1.27
     colis
    1.27
     his
    1.25
    ilization
    1.23
     crê
    1.20
    polish
    1.18
    oteric
    1.16
    projectName
    1.16
    Activations Density 0.120%

    No Known Activations