© 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. 10-GEMMASCOPE-RES-131K
    7. 123547
    Prev
    Next
    INDEX
    Explanations

    vehicle components and systems

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

    The neuron activates strongly on terminology referring to vehicle control systems—especially words like “control,” “system(s),” and related components in automotive or engine contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    thisis
    -1.17
    ..\..\
    -1.16
     already
    -1.09
    閲覧
    -1.05
     llam
    -1.05
    rinology
    -1.04
    uksia
    -1.03
    зык
    -1.03
    digm
    -1.03
     држа
    -1.02
    POSITIVE LOGITS
    According
    1.13
     foglie
    1.13
     проблема
    1.10
    攝
    1.08
     изготовления
    1.05
     parcheggio
    1.05
     которые
    1.04
    諷
    1.02
     manifestazione
    1.02
    чек
    1.01
    Activations Density 0.183%

    No Known Activations