© 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. 93689
    Prev
    Next
    INDEX
    Explanations

    complex mixtures and components

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

    scientific or technical phrases related to chemical compounds and mixtures.

    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
    LETED
    -0.79
     SPSS
    -0.79
     расход
    -0.78
    mousedown
    -0.72
    [-
    -0.71
     yew
    -0.69
     Protein
    -0.69
     János
    -0.68
     ♪
    -0.68
     protein
    -0.68
    POSITIVE LOGITS
     mixture
    5.38
     mixtures
    4.41
     mix
    4.09
    mixture
    3.97
     Mixture
    3.97
    Mixture
    3.86
     Mixtures
    3.63
     blend
    3.47
     mixed
    3.39
    混合
    3.23
    Activations Density 0.238%

    No Known Activations