© 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. 7940
    Prev
    Next
    INDEX
    Explanations

    crystal structure systems

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

    crystal structure types like monoclinic, trigonal, tetragonal, and rhombohedral in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on terms naming crystal‐structure symmetries or lattice systems (e.g. monoclinic, trigonal, tetragonal, cubic, hexagonal, hombohedral, 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_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
    鸲
    -1.63
    вания
    -1.58
    鼍
    -1.52
    ᯾
    -1.52
     stary
    -1.45
    ViewFeatures
    -1.43
    journalist
    -1.42
     článek
    -1.41
    brtc
    -1.41
    istiques
    -1.38
    POSITIVE LOGITS
     decorados
    1.48
     misguided
    1.43
     antiguas
    1.41
     southeast
    1.39
     químico
    1.38
     fisuras
    1.38
     decoradas
    1.36
     unrelenting
    1.36
     personalizados
    1.36
     montañas
    1.35
    Activations Density 0.052%

    No Known Activations