© 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. 68330
    Prev
    Next
    INDEX
    Explanations

    spices like turmeric and cumin

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

    chemical compounds and spices, particularly curcumin and turmeric.

    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
    {
    -2.73
     With
    -2.69
    In
    -2.67
     This
    -2.58
     midst
    -2.58
     Importantly
    -2.42
     Assuming
    -2.34
     Personally
    -2.34
     Included
    -2.30
     Notwithstanding
    -2.30
    POSITIVE LOGITS
    釓
    2.19
    芣
    2.14
     inspiradoras
    2.02
     fantástica
    2.00
    从未
    2.00
     truk
    1.98
    which
    1.96
     сына
    1.95
    ↑↑↑</
    1.95
     høy
    1.94
    Activations Density 0.010%

    No Known Activations