© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108949
    Prev
    Next
    INDEX
    Explanations

    Russian and Ukrainian cities and districts

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

    The neuron activates on Russian or former‐Soviet place names and administrative regions (e.g. toponyms ending in –sk, –ov, –sky, –ovo, etc.).

    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
    Pulitzer
    -0.85
    Profesor
    -0.84
     additionally
    -0.78
     likewise
    -0.78
    Additionally
    -0.77
     to
    -0.75
     analisis
    -0.74
     politika
    -0.74
     diría
    -0.73
    etera
    -0.73
    POSITIVE LOGITS
     branch
    1.02
    سری
    0.95
     itinéraire
    0.90
    lides
    0.90
    Joel
    0.90
     réservoir
    0.90
    Oil
    0.89
    سرو
    0.88
    Törté
    0.88
    Messages
    0.88
    Activations Density 0.023%

    No Known Activations