© 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. 47762
    Prev
    Next
    INDEX
    Explanations

    Google products and services

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

    The neuron fires on mentions of Google Assistant—its name, invocation phrases, and descriptions of its features or updates.

    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
    ська
    -0.81
    Amazon
    -0.75
     Amazon
    -0.73
    квар
    -0.72
    Town
    -0.71
    学院
    -0.71
    にご
    -0.71
     Warrington
    -0.71
     Town
    -0.70
    errHandler
    -0.70
    POSITIVE LOGITS
     Nest
    0.92
    Nest
    0.88
     Assistant
    0.87
     Stadia
    0.86
    のエ
    0.80
     firebase
    0.80
    Google
    0.80
    Ⓘ
    0.78
     Byzantium
    0.78
    CONTINUED
    0.78
    Activations Density 0.039%

    No Known Activations