© 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. 91365
    Prev
    Next
    INDEX
    Explanations

    thermodynamics and kJ

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

    chemistry-related content, especially numerical values for chemical reactions and formulations.

    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
    诺
    -0.79
     genius
    -0.77
    ыл
    -0.75
    भार
    -0.72
     tbsp
    -0.72
     Toen
    -0.72
    BoxLayout
    -0.71
     nail
    -0.71
    deme
    -0.70
     prest
    -0.69
    POSITIVE LOGITS
     Hess
    0.95
    kJ
    0.93
     calorimeter
    0.90
     kJ
    0.85
     calor
    0.82
     therm
    0.81
    PageIndex
    0.81
    othermic
    0.80
    )=-
    0.78
    }=-
    0.75
    Activations Density 0.020%

    No Known Activations