© 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. 84169
    Prev
    Next
    INDEX
    Explanations

    engine operation and technology

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

    The main thing this neuron does is detect mentions of engines or engine-related discussion.

    oai_token-act-pair · o4-miniTriggered 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
    Ꭺ
    -1.19
    生效
    -1.13
    al
    -1.10
    tion
    -1.09
     varför
    -1.09
    尔的
    -1.09
    taz
    -1.07
    卽
    -1.05
    able
    -1.05
    lerine
    -1.03
    POSITIVE LOGITS
     engine
    1.46
     performance
    1.30
     engines
    1.23
    を搭載
    1.20
    یات
    1.19
    VIATIONS
    1.18
     potrebné
    1.16
     power
    1.14
     apartament
    1.13
     leerlingen
    1.12
    Activations Density 0.061%

    No Known Activations