© 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. 34-GEMMASCOPE-RES-131K
    4. 73641
    Prev
    Next
    INDEX
    Explanations

    engine intake manifold

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

    The neuron activates on technical terms referring to internal‐combustion engine air‐intake components (e.g. intake, port, carburetor, manifold).

    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
    Fuk
    -0.81
    Lact
    -0.79
    nob
    -0.71
    ดิน
    -0.71
     oír
    -0.69
    ніе
    -0.69
    輟
    -0.68
     Puebla
    -0.67
    レバー
    -0.66
     banging
    -0.65
    POSITIVE LOGITS
     throttle
    1.72
     intake
    1.29
     IAC
    1.23
     Throttle
    1.18
    throttle
    1.14
     runners
    1.13
     manifold
    1.13
     intakes
    1.11
    IAC
    1.08
    manifold
    1.07
    Activations Density 0.017%

    No Known Activations