© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8948
    Prev
    Next
    INDEX
    Explanations

    starch and gelatin compounds

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

    food ingredients and scientific compounds, particularly starches and gelatin.

    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
    ارتمان
    -1.38
     فريبيس
    -1.38
    тное
    -1.37
     "..\..\..\
    -1.31
    ковь
    -1.29
    ࿆
    -1.27
    骝
    -1.26
    County
    -1.24
     高
    -1.23
    樘
    -1.23
    POSITIVE LOGITS
    {
    1.51
    ,"
    1.24
    </h2>
    1.23
    s
    1.21
     \&
    1.19
     et
    1.16
    #,
    1.14
    ,<
    1.11
    "
    1.11
    ]
    1.10
    Activations Density 0.074%

    No Known Activations