© 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. 98108
    Prev
    Next
    INDEX
    Explanations

    metal-organic frameworks

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

    scientific terminology related to metal-organic frameworks (MOFs) and porous materials.

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

    This neuron responds to chemical‐formula or material‐name tokens (e.g. metal–organic framework designations like “Mg-MOF-74,” “CO₂,” or “M₁₂O₈(μ₃-O)₈” ).

    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
    avut
    -0.78
     strikeouts
    -0.75
    ாம்
    -0.75
    Medien
    -0.74
    ત્
    -0.74
     Pfund
    -0.73
    cokinetics
    -0.71
    ністю
    -0.71
    CEEDED
    -0.71
    男子
    -0.69
    POSITIVE LOGITS
     Ui
    0.98
     guest
    0.94
    Framework
    0.92
    framework
    0.91
     framework
    0.88
     guests
    0.85
     linker
    0.85
     MIL
    0.84
    guest
    0.82
    MIL
    0.81
    Activations Density 0.077%

    No Known Activations