© 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. 69937
    Prev
    Next
    INDEX
    Explanations

    Holly and Lewis names

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

    The neuron strongly activates on capitalized personal first names (e.g. “Holly,” “Lewis”).

    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
     entstanden
    -2.53
    ذ
    -2.47
     traditionellen
    -2.47
    咐
    -2.45
    銠
    -2.44
    er
    -2.42
     halben
    -2.39
     больших
    -2.31
     ‎
    -2.31
     akin
    -2.28
    POSITIVE LOGITS
    柃
    2.84
    錒
    2.45
    衎
    2.28
     tungkol
    2.28
    所说
    2.25
    اعمال
    2.25
     russ
    2.23
    哢
    2.23
    ндарт
    2.22
     związane
    2.22
    Activations Density 0.003%

    No Known Activations