© 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. 99386
    Prev
    Next
    INDEX
    Explanations

    BSD license

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

    The neuron is detecting mentions of “S3” (AWS S3) references, i.e. tokens related to S3 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
    ไม
    -0.87
     Wii
    -0.72
     ballast
    -0.71
     keyring
    -0.71
     Stainless
    -0.71
    兒童
    -0.70
     tạp
    -0.69
     وهي
    -0.69
    으며
    -0.68
     tenement
    -0.68
    POSITIVE LOGITS
    ervices
    0.73
    転
    0.71
     á
    0.70
    RETRY
    0.70
    лександр
    0.68
     amazon
    0.68
     Prze
    0.68
    wek
    0.68
     dok
    0.67
    ite
    0.66
    Activations Density 0.039%

    No Known Activations