© 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. 10-GEMMASCOPE-RES-131K
    7. 42547
    Prev
    Next
    INDEX
    Explanations

    parachutes, falling, or ejection

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

    The neuron strongly activates on words and phrases referring to parachutes or related airborne safety/ejection gear (e.g., parachute, skydivers, airborne ejection seats).

    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
     you
    -1.78
     Públicas
    -1.70
    st
    -1.62
    ℣
    -1.59
    replyreport
    -1.59
    ⎽
    -1.59
    al
    -1.58
    ？）
    -1.55
    鐃
    -1.53
    在其
    -1.52
    POSITIVE LOGITS
    e
    2.11
    趿
    1.89
    齪
    1.81
    崤
    1.73
    </h1>
    1.64
    \\
    1.63
     "
    1.63
    --
    1.63
    ଞ
    1.57
     häufigsten
    1.55
    Activations Density 0.012%

    No Known Activations