© 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. 13456
    Prev
    Next
    INDEX
    Explanations

    artist and band names

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

    The neuron fires on capitalized proper names—especially celebrity, artist, and band 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
    ↵
    -1.30
    イヤレス
    -1.14
    ⲁ
    -1.09
     coinc
    -1.07
             
    -1.07
     exclaim
    -1.07
     avenge
    -1.06
     essere
    -1.06
    k
    -1.05
     of
    -1.05
    POSITIVE LOGITS
    zieren
    1.34
    鮠
    1.30
     kabát
    1.27
     khác
    1.23
     usuário
    1.20
     vás
    1.18
    橚
    1.16
    iciar
    1.16
    鼋
    1.14
    廔
    1.13
    Activations Density 0.059%

    No Known Activations