© 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. 130214
    Prev
    Next
    INDEX
    Explanations

    places and names

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

    The neuron detects capitalized proper names—i.e. named-entity tokens such as people’s surnames and 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
    -4.38
    4
    -4.31
    8
    -3.86
    0
    -3.73
     {
    -3.66
    3
    -3.61
    re
    -3.59
    c
    -3.48
    9
    -3.41
    A
    -3.36
    POSITIVE LOGITS
    ’，
    2.86
    佾
    2.77
    逦
    2.70
    OUTUBE
    2.69
    ндарт
    2.58
    🥵
    2.56
    💃
    2.48
    ᠌
    2.48
    粍
    2.48
     玩具
    2.42
    Activations Density 0.015%

    No Known Activations