© 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. 47720
    Prev
    Next
    INDEX
    Explanations

    vacuum systems and applications

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

    The main thing this neuron does is detect mentions of vacuum-related apparatus or components.

    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
     الحم
    -0.90
    getreten
    -0.85
     courtiers
    -0.85
    Jurassic
    -0.84
    ebaran
    -0.81
     封面
    -0.78
    蚨
    -0.78
     tain
    -0.78
    可以说
    -0.77
    Noticia
    -0.77
    POSITIVE LOGITS
     sucks
    0.93
    Vac
    0.84
     ultraviolet
    0.83
    STATE
    0.81
    assisted
    0.79
    チャン
    0.79
     created
    0.76
     شد
    0.76
     Vac
    0.75
     chamber
    0.75
    Activations Density 0.014%

    No Known Activations