© 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. 34-GEMMASCOPE-RES-131K
    7. 30878
    Prev
    Next
    INDEX
    Explanations

    molecular connectivity and density functional theory

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

    This neuron detects computational chemistry and quantum mechanics terminology, particularly focusing on molecular orbital calculations and theoretical methods.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     maxed
    -0.75
     wreckage
    -0.74
    ometro
    -0.72
    jaan
    -0.72
    poko
    -0.70
    Losses
    -0.69
    spieler
    -0.68
    ROL
    -0.68
    piz
    -0.67
     fraudul
    -0.67
    POSITIVE LOGITS
     overlap
    1.07
    overlap
    0.94
    Overlap
    0.90
     mixing
    0.88
     Zeus
    0.80
     LCA
    0.79
    Mixing
    0.78
     Mixing
    0.77
     Wishing
    0.74
    LCA
    0.72
    Activations Density 0.050%

    No Known Activations