© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108813
    Prev
    Next
    INDEX
    Explanations

    planets and protoplanetary discs

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

    The neuron fires on specialized planetary‐science jargon—especially morphemes of “protoplanetary” and related terms describing planets and discs in astrophysics abstracts.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Perl
    -0.81
     perl
    -0.80
     Saline
    -0.79
    SOIL
    -0.76
     strepto
    -0.75
     mussels
    -0.75
     lobsters
    -0.75
    ְּ
    -0.75
     soaps
    -0.74
     Quilt
    -0.73
    POSITIVE LOGITS
     planet
    1.08
     disk
    0.99
     planets
    0.94
     embryo
    0.93
     fragmentation
    0.90
     embryos
    0.83
     icy
    0.83
     planeta
    0.83
     Planet
    0.82
     migration
    0.81
    Activations Density 0.029%

    No Known Activations