© 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. 40980
    Prev
    Next
    INDEX
    Explanations

    dendritic cells and TLRs

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

    terms related to immune system cells, particularly dendritic cells and their receptors.

    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
     Penyakit
    -1.64
    卄
    -1.62
    訁
    -1.52
    értelmű
    -1.48
    обои
    -1.48
     joyeux
    -1.43
    НІ
    -1.43
     vermel
    -1.41
     邸
    -1.39
     concepción
    -1.39
    POSITIVE LOGITS
    ↵↵
    1.69
     guiding
    1.55
    .”
    1.54
    无需
    1.53
    </strong>
    1.48
     upsetting
    1.44
    U
    1.38
     are
    1.32
     shutting
    1.31
    雛
    1.31
    Activations Density 0.073%

    No Known Activations