© 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. 14549
    Prev
    Next
    INDEX
    Explanations

    celestial objects and astral travel

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

    The main thing this neuron does is identify words referring to celestial or astronomical concepts.

    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
    quelize
    -2.72
    摶
    -2.61
     mété
    -2.53
     pauvreté
    -2.50
    antaranya
    -2.45
    akaian
    -2.41
    osť
    -2.39
     fiabilité
    -2.39
    塒
    -2.38
    媜
    -2.36
    POSITIVE LOGITS
    {
    3.58
    ,“
    3.09
    *
    2.67
     
    2.50
    ]
    2.48
     “
    2.39
    ский
    2.36
    “
    2.30
    ↵
    2.23
     portray
    2.19
    Activations Density 0.002%

    No Known Activations