© 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. 128358
    Prev
    Next
    INDEX
    Explanations

    crystallization, crystalline, crystal forms

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

    words related to crystal structures and crystallization processes in scientific contexts.

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

    The neuron is specialized in detecting mentions of crystallization or crystal-related terms.

    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
    ↵↵
    -2.42
     extraordinaire
    -2.14
    푔
    -2.00
     whirlwind
    -1.84
     fabbrica
    -1.83
    都在
    -1.80
     generazione
    -1.79
    猡
    -1.79
     speculating
    -1.77
    龶
    -1.76
    POSITIVE LOGITS
    ”:
    2.59
    ,“
    2.59
    ៚
    2.41
    !”
    2.34
    “
    2.13
     encantador
    1.98
    :“
    1.96
     участники
    1.95
    .’’
    1.92
     Дмитри
    1.88
    Activations Density 0.021%

    No Known Activations