© 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. 34-GEMMASCOPE-RES-131K
    7. 84796
    Prev
    Next
    INDEX
    Explanations

    white dwarf, nebula, magnetic star

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

    The neuron fires on specialized astrophysics jargon, especially terms related to compact stellar remnants and their physical processes (e.g. “degenerate,” “white dwarf,” “planetary nebula nucleus,” “convective,” “nova,” etc.).

    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
     discursos
    -0.81
    criminate
    -0.76
     cement
    -0.76
    bib
    -0.75
    返
    -0.75
    handed
    -0.74
     MotionEvent
    -0.73
    鶏
    -0.73
    煲
    -0.72
    ynı
    -0.69
    POSITIVE LOGITS
     WD
    0.99
     white
    0.93
     Sion
    0.85
     Sirius
    0.84
     wd
    0.82
    白
    0.82
     weiße
    0.78
     Helium
    0.77
     LEA
    0.77
     searcher
    0.76
    Activations Density 0.035%

    No Known Activations