© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44613
    Prev
    Next
    INDEX
    Explanations

    Republic, virtual machine

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

    This neuron activates on multiword named-entity phrases made of consecutive capitalized words (e.g. “Central African Republic,” “Virtual Machine”).

    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
     \&
    -1.70
    f
    -1.70
     físicas
    -1.68
    p
    -1.62
     internas
    -1.62
     wenn
    -1.62
    b
    -1.55
    𖧷
    -1.55
     nella
    -1.51
    買う
    -1.48
    POSITIVE LOGITS
    <bos>
    1.77
     ſta
    1.71
     hetzelfde
    1.53
     gesprek
    1.48
     ſy
    1.47
    СЯ
    1.45
     recuper
    1.41
    韪
    1.41
    挲
    1.41
     äußerst
    1.40
    Activations Density 0.059%

    No Known Activations