© 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. 10-GEMMASCOPE-RES-131K
    7. 41045
    Prev
    Next
    INDEX
    Explanations

    place names and past tense verbs

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

    The neuron detects long, multi‐syllable fragments of proper names—especially geographic or place names.

    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
    ↵↵
    -1.82
    </h2>
    -1.62
    -1.55
    </b>
    -1.50
    vább
    -1.49
    uyasha
    -1.49
    teries
    -1.48
          
    -1.47
     you
    -1.46
     endast
    -1.43
    POSITIVE LOGITS
     tomaron
    1.95
     recibieron
    1.93
     decidieron
    1.74
     zmieni
    1.73
     realizaron
    1.70
     presentaron
    1.67
     pensiero
    1.66
     Primeiro
    1.66
     informaron
    1.65
     successivo
    1.64
    Activations Density 0.092%

    No Known Activations