© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30007
    Prev
    Next
    INDEX
    Explanations

    quantum mechanics and molecular structure

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

    scientific parameters and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Citizens
    0.49
    运营商
    0.48
     marchandises
    0.48
    运维
    0.48
    经纪
    0.48
     citoyens
    0.46
     truckers
    0.46
    🚚
    0.46
    设备的
    0.46
     autobús
    0.45
    POSITIVE LOGITS
     orbitals
    0.90
     atoms
    0.85
     solvation
    0.79
     molecule
    0.75
     chemistry
    0.73
    molecule
    0.73
     molecules
    0.72
     Chemistry
    0.72
     molecular
    0.71
     covalent
    0.70
    Activations Density 0.026%

    No Known Activations