© 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. 91195
    Prev
    Next
    INDEX
    Explanations

    google projects

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

    The neuron fires on mentions of Google’s self-driving car news (e.g. “Google,” “car,” “autonomous,” police stop, driving too slowly) — in other words, it detects articles about Google’s automotive/autonomous-vehicle projects.

    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
    视着
    -0.86
     tây
    -0.78
    微信
    -0.77
     cưới
    -0.75
     Sneaker
    -0.73
     cero
    -0.72
    يا
    -0.68
     sosial
    -0.68
    prepareStatement
    -0.68
    我的
    -0.67
    POSITIVE LOGITS
     Google
    2.39
    Google
    2.05
    GOOGLE
    1.82
     GOOGLE
    1.67
     Alphabet
    1.65
     google
    1.62
     Goo
    1.61
    google
    1.41
    Goo
    1.40
     goog
    1.35
    Activations Density 0.053%

    No Known Activations