© 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. 58034
    Prev
    Next
    INDEX
    Explanations

    air intake and engine components

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

    The neuron flags technical phrases that describe drawing, measuring, or compressing airflow (e.g. “draws air in through a compressor housing,” “mass air flow meter”).

    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
     Kuz
    -0.77
    𝙳
    -0.70
     المسؤول
    -0.70
     Xuan
    -0.69
     döne
    -0.68
     Niko
    -0.67
    katakan
    -0.67
     EXTER
    -0.67
    닙
    -0.66
    下一页
    -0.65
    POSITIVE LOGITS
     intake
    1.74
     filter
    1.56
     air
    1.50
    intake
    1.34
     Intake
    1.33
    filter
    1.31
     Filter
    1.30
     MAF
    1.30
     filtro
    1.29
     oiled
    1.24
    Activations Density 0.011%

    No Known Activations