© 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. 10-GEMMASCOPE-RES-131K
    7. 67999
    Prev
    Next
    INDEX
    Explanations

    mission, missionary, missions

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

    The neuron activates specifically on occurrences of the word “Mission” (often capitalized) in text.

    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
    衚
    -3.39
    uſe
    -3.06
     інших
    -2.86
    苼
    -2.77
    对方的
    -2.75
    jdons
    -2.73
    ではまた
    -2.70
     Мария
    -2.66
    蚋
    -2.59
    魨
    -2.58
    POSITIVE LOGITS
    ↵
    4.22
    ’
    3.52
    at
    3.02
    也
    2.75
    ”
    2.73
    </b>
    2.70
    ↵↵
    2.63
     For
    2.58
    .
    2.55
    ,
    2.55
    Activations Density 0.007%

    No Known Activations