© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106177
    Prev
    Next
    INDEX
    Explanations

    spacecraft and travel

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

    The main thing this neuron does is detect space‐ and sci-fi–themed terms.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ARGB
    -0.90
     Innenstadt
    -0.82
    水槽
    -0.80
     Godzilla
    -0.80
    chtest
    -0.79
     hemat
    -0.76
     ultrason
    -0.75
     helicopters
    -0.74
     bicycle
    -0.73
     NIE
    -0.73
    POSITIVE LOGITS
     space
    2.05
     spaceship
    1.87
     planet
    1.80
     Space
    1.75
    Space
    1.67
    space
    1.66
     planets
    1.66
     spacecraft
    1.60
     galactic
    1.52
    SPACE
    1.48
    Activations Density 0.053%

    No Known Activations