© 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. 38672
    Prev
    Next
    INDEX
    Explanations

    gas mixtures and compositions

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

    measurements or concentrations of gases like oxygen, carbon monoxide, or nitrogen in scientific contexts.

    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
     dissolved
    -1.05
    昱
    -0.95
     Dissolved
    -0.84
     září
    -0.77
    刨
    -0.75
    diss
    -0.71
    tmpdir
    -0.71
    ışık
    -0.70
    pielt
    -0.69
     đầm
    -0.69
    POSITIVE LOGITS
     composition
    0.90
     dilu
    0.81
     mixtures
    0.76
     percentage
    0.76
     percentages
    0.75
     volum
    0.75
     compositions
    0.74
     Balan
    0.74
     fossi
    0.73
     mole
    0.71
    Activations Density 0.040%

    No Known Activations