© 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. 69895
    Prev
    Next
    INDEX
    Explanations

    JAK, STAT, IRS signaling

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

    cell signaling pathway proteins, particularly STAT, JAK, and receptor-related molecules in scientific 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
    ";
    -1.76
    ,"
    -1.59
     -
    -1.59
     "
    -1.56
    3
    -1.53
    。"
    -1.48
    i
    -1.46
    </h3>
    -1.45
    ""
    -1.43
     In
    -1.38
    POSITIVE LOGITS
    )");
    1.64
    
    1.55
    jandra
    1.49
    鰱
    1.49
    edded
    1.48
     ),
    1.48
    Toute
    1.46
     télécharge
    1.45
     decât
    1.43
    縯
    1.41
    Activations Density 0.069%

    No Known Activations