© 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. 34-GEMMASCOPE-RES-131K
    7. 99158
    Prev
    Next
    INDEX
    Explanations

    uploading documents or files

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

    This neuron activates on file‐related terms in technical contexts (e.g. file, files, upload, path, pdf, attachments).

    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
    bigl
    -0.86
    ностей
    -0.84
    кипедия
    -0.84
    andescent
    -0.83
    ORPG
    -0.82
    edade
    -0.81
     ^
    -0.79
     Christ
    -0.79
    彰
    -0.79
    rainian
    -0.78
    POSITIVE LOGITS
     document
    2.02
     file
    1.98
     uploaded
    1.90
     files
    1.84
     documents
    1.83
     upload
    1.70
     dokumen
    1.55
     attachments
    1.53
    upload
    1.49
     uploading
    1.49
    Activations Density 0.022%

    No Known Activations