© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1195
    Prev
    Next
    INDEX
    Explanations

    calculated molecular weight

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

    descriptions of molecular weights, particularly in scientific papers discussing proteins.

    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
    ikin
    -0.95
    øb
    -0.79
    medio
    -0.77
    imdi
    -0.74
    spend
    -0.73
    menistan
    -0.71
    arya
    -0.70
    bui
    -0.70
    GL
    -0.69
    blame
    -0.69
    POSITIVE LOGITS
     molecular
    2.41
     molar
    2.20
     MW
    1.95
     Molecular
    1.90
     atomic
    1.85
    Molecular
    1.80
    molecular
    1.78
    MW
    1.58
     молеку
    1.46
    atomic
    1.45
    Activations Density 0.092%

    No Known Activations