© 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. 10-GEMMASCOPE-RES-131K
    7. 84353
    Prev
    Next
    INDEX
    Explanations

    actinomycete antibiotics

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

    scientific or technical terms, particularly chemical compounds, biological organisms, and specialized nomenclature.

    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_10/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
     cinto
    -1.82
    桖
    -1.81
     alho
    -1.80
     tomba
    -1.65
     violon
    -1.64
     inuti
    -1.63
     mals
    -1.63
     elegante
    -1.61
    <bos>
    -1.60
     vendredi
    -1.60
    POSITIVE LOGITS
     DÍA
    1.89
    </sub>
    1.83
    \}
    1.70
     flesta
    1.69
     after
    1.68
     черная
    1.67
    什么呢
    1.65
     desire
    1.64
    沨
    1.63
     того
    1.62
    Activations Density 0.089%

    No Known Activations