© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92765
    Prev
    Next
    INDEX
    Explanations

    iTunes and Apple services

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

    The neuron strongly activates on mentions of iTunes (and closely related digital‐media distribution/download terms such as podcasts, apps, purchase, and download).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     unfolding
    -0.75
    릇
    -0.74
     sedentary
    -0.71
    nextLine
    -0.71
    ڼ
    -0.71
    úcia
    -0.69
    кро
    -0.68
     dumped
    -0.68
     %}
    -0.68
    upa
    -0.68
    POSITIVE LOGITS
     iTunes
    1.96
     Apple
    1.61
    Apple
    1.43
    iTunes
    1.43
     itunes
    1.38
    apple
    1.30
     apple
    1.30
     Apples
    1.15
    itunes
    1.15
     manzana
    1.02
    Activations Density 0.043%

    No Known Activations