© 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. 14360
    Prev
    Next
    INDEX
    Explanations

    stem cell research and therapy

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

    The neuron detects the phrase "stem cell" and related terminology in scientific/medical 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
     lesquelles
    -1.77
     ہے۔
    -1.73
    類型
    -1.70
    總是
    -1.69
     طلا
    -1.68
     キャップ
    -1.65
    "$_
    -1.64
    畫面
    -1.63
    記錄
    -1.63
    都在
    -1.62
    POSITIVE LOGITS
    ?”
    2.33
     ”
    2.22
     have
    2.05
    ’
    1.88
    </strong>
    1.84
     favoritas
    1.81
     була
    1.75
    ”:
    1.74
     материалов
    1.74
     diskusi
    1.73
    Activations Density 0.015%

    No Known Activations