© 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. 10-GEMMASCOPE-RES-131K
    7. 85051
    Prev
    Next
    INDEX
    Explanations

    garlic and bread

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

    references to garlic and other ingredients in culinary contexts.

    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
     raiſ
    -1.93
    鲥
    -1.92
    ⢪
    -1.90
    𐍆
    -1.83
     pengar
    -1.83
     laine
    -1.82
     språk
    -1.81
     entrado
    -1.81
     deſt
    -1.80
     annons
    -1.80
    POSITIVE LOGITS
    }
    2.44
     Our
    1.87
    ."
    1.84
     {
    1.73
    }$
    1.73
    mopol
    1.71
    </h1>
    1.70
    chitz
    1.66
     mejora
    1.66
     trabalho
    1.66
    Activations Density 0.008%

    No Known Activations