© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102663
    Prev
    Next
    INDEX
    Explanations

    engine boosting systems

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

    The neuron fires on technical terms naming components or operations that increase pressure or boost performance (e.g. “boosting,” “brake booster,” “turbo­charged,” “hydraulic pressure”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     addirittura
    -1.42
    ௅
    -1.35
     varför
    -1.22
    ⬮
    -1.22
     моего
    -1.22
    ープン
    -1.21
    gång
    -1.21
     będ
    -1.21
     białym
    -1.21
     ideen
    -1.20
    POSITIVE LOGITS
     which
    1.48
     is
    1.36
     —
    1.28
     –
    1.25
    Ⅰ
    1.21
    ográfico
    1.20
     не
    1.18
    Ɲ
    1.14
     >
    1.13
     >>=
    1.13
    Activations Density 0.086%

    No Known Activations