© 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. 30733
    Prev
    Next
    INDEX
    Explanations

    hydrocarbon processing fuels oils

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

    chemical terms and compounds in scientific/technical texts about petroleum, hydrocarbons, and chemical processes.

    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
    IFS
    -0.79
     Geometry
    -0.77
     Blaise
    -0.69
     bào
    -0.69
     Dhaka
    -0.69
     factory
    -0.69
     انا
    -0.69
    intura
    -0.68
    ByUserId
    -0.68
    deriv
    -0.67
    POSITIVE LOGITS
     arom
    1.00
     Anche
    0.92
     hetero
    0.89
     asfal
    0.86
    halten
    0.85
     oils
    0.85
     Asphalt
    0.82
     royalty
    0.82
     масла
    0.82
     koo
    0.80
    Activations Density 0.050%

    No Known Activations