© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98684
    Prev
    Next
    INDEX
    Explanations

    time and activities

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

    The neuron responds to descriptions of driving events, especially first-person accounts of operating a vehicle (e.g. “I was driving,” “driving,” “broke down while driving”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    first-person narratives describing personal experiences or activities.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of vehicle operation and travel on the road, including driving, trips, and related motion or conditions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.49
     there
    -1.28
     already
    -1.21
    lántico
    -1.18
    晌
    -1.13
     aliran
    -1.11
     Lessing
    -1.11
    ناصر
    -1.09
     Dichtung
    -1.09
    cích
    -1.08
    POSITIVE LOGITS
     音乐
    1.41
     test
    1.23
     frequentemente
    1.20
    ใช้งาน
    1.19
     performance
    1.16
     montagne
    1.11
     Teilnahme
    1.08
     режи
    1.07
     "/
    1.06
     benutzt
    1.06
    Activations Density 0.023%

    No Known Activations