© 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. 22-GEMMASCOPE-RES-131K
    7. 69143
    Prev
    Next
    INDEX
    Explanations

    tools and equipment

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

    The neuron strongly activates on mentions of specialized tools, machines, and scientific instruments (e.g. “machine,” “drill,” “sprayer,” “microscope,” “spectrometer,” etc.).

    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
     たち
    -1.16
     previos
    -1.12
     ettei
    -1.10
     ï
    -1.09
     vaikka
    -1.07
    ются
    -1.06
    valents
    -1.05
    為に
    -1.05
     intrigu
    -1.03
     kwamba
    -1.03
    POSITIVE LOGITS
     scanner
    1.09
    やろ
    1.06
     pistola
    1.03
     аппара
    1.02
     same
    1.02
     used
    1.01
     bobina
    1.01
    บุรี
    0.98
     tonel
    0.97
     capability
    0.96
    Activations Density 0.137%

    No Known Activations