© 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. 22-GEMMASCOPE-RES-131K
    7. 14711
    Prev
    Next
    INDEX
    Explanations

    medieval items and artists

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

    This neuron strongly activates on plural common nouns.

    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
     präsenti
    -1.02
     särsk
    -1.01
     vorhandenen
    -1.00
     bestehende
    -0.97
     vorhand
    -0.96
     bestehenden
    -0.96
     /*
    -0.94
     größten
    -0.93
     numerosos
    -0.92
     ergän
    -0.90
    POSITIVE LOGITS
     and
    1.15
     pazar
    1.02
    горит
    1.02
     lez
    0.96
    省市镇
    0.95
    الى
    0.94
    hammed
    0.92
    эт
    0.90
     that
    0.89
     devez
    0.89
    Activations Density 0.082%

    No Known Activations