© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76365
    Prev
    Next
    INDEX
    Explanations

    cloud storage services

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

    The neuron strongly activates on mentions of cloud‐based file storage and synchronization services (e.g. Drive, Dropbox, cloud storage).

    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
    amino
    -0.91
    沓
    -0.82
    tawesome
    -0.76
    ільки
    -0.76
    jewództ
    -0.76
     twitter
    -0.74
     currency
    -0.74
    鴉
    -0.73
    uParam
    -0.73
    áv
    -0.73
    POSITIVE LOGITS
     storage
    3.08
    storage
    2.55
     Storage
    2.45
     cloud
    2.36
    Storage
    2.34
     STORAGE
    2.20
    STORAGE
    2.16
     almacenamiento
    2.00
     Cloud
    1.91
     storing
    1.91
    Activations Density 0.050%

    No Known Activations