© 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. 20604
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles

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

    The neuron fires on capitalized proper names and titles—especially brand names, comic‐book characters, and product 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
     ideen
    -1.73
     voren
    -1.63
     preferências
    -1.61
     upacara
    -1.58
    Ꮵ
    -1.56
     gewor
    -1.53
     nimmer
    -1.53
     musli
    -1.52
     konsult
    -1.52
     SCHOLASTIC
    -1.50
    POSITIVE LOGITS
     e
    1.53
     B
    1.52
     längere
    1.45
     The
    1.45
     sorta
    1.43
     Year
    1.40
     U
    1.38
     H
    1.38
     l
    1.37
     p
    1.36
    Activations Density 0.005%

    No Known Activations