© 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. 58893
    Prev
    Next
    INDEX
    Explanations

    fraternity and love for people

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

    This neuron fires on personal‐experience travelogue language—especially first-person plural narration (“we,” “have,” “lived,” “traveled”) with emotive/descriptive words describing feelings, places, and events.

    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
    閒
    -0.87
     locale
    -0.85
    дакти
    -0.84
    經典
    -0.84
     eski
    -0.82
     sfeer
    -0.82
     atmosphere
    -0.81
    詳しく
    -0.81
     matrimonio
    -0.81
    ktionen
    -0.79
    POSITIVE LOGITS
    ALSE
    1.02
     fraternal
    0.95
     τῆς
    0.94
     Fraternity
    0.91
     simplu
    0.90
    땐
    0.89
     dissim
    0.87
    titudine
    0.87
    acidade
    0.86
     ilu
    0.85
    Activations Density 0.022%

    No Known Activations