© 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. 89920
    Prev
    Next
    INDEX
    Explanations

    crystal, crystalline, crystallinity

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

    The neuron strongly responds to terms and phrases that denote crystalline structure or crystallinity in materials‐science contexts.

    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
    ESSO
    -0.88
     Clément
    -0.80
    тр
    -0.79
    日報
    -0.77
     erwartet
    -0.72
    albero
    -0.70
     چسب
    -0.69
     Silvia
    -0.69
    clickable
    -0.67
     proy
    -0.67
    POSITIVE LOGITS
     crystall
    1.89
     crystal
    1.56
     Crystal
    1.50
    Crystal
    1.45
    crystal
    1.39
     crystalline
    1.38
    rystal
    1.19
     crystals
    1.13
     Cry
    1.13
     crist
    1.10
    Activations Density 0.054%

    No Known Activations