© 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. 34-GEMMASCOPE-RES-131K
    7. 60263
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron is strongly activated by proper names and citations—especially personal names, author or translator attributions, and titled references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Ελλά
    -0.88
    guei
    -0.86
    metazone
    -0.80
    对应
    -0.78
     incó
    -0.77
    Diagnostics
    -0.73
    섭
    -0.73
    gamos
    -0.71
    ivel
    -0.70
    jPanel
    -0.69
    POSITIVE LOGITS
     narrated
    1.61
     reported
    1.55
     narration
    1.41
     transmission
    1.22
     Transmission
    1.20
     narrator
    1.18
    Reported
    1.16
     transmitted
    1.13
     narr
    1.13
     Narr
    1.10
    Activations Density 0.007%

    No Known Activations