© 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. 66632
    Prev
    Next
    INDEX
    Explanations

    Regina Rage / Adel skalen

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

    This neuron detects capitalized proper names—particularly place and organization 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
    不错的
    -2.64
     are
    -2.55
     {
    -2.55
    衚
    -2.44
     видел
    -2.30
    руют
    -2.30
    鲠
    -2.30
     "
    -2.28
     kurzem
    -2.27
    鬭
    -2.25
    POSITIVE LOGITS
    (“
    2.78
    "
    2.61
     ovunque
    2.59
    鳢
    2.59
     レスト
    2.50
     multitude
    2.48
    ྂ
    2.47
    褫
    2.45
     varieties
    2.41
     errone
    2.41
    Activations Density 0.003%

    No Known Activations