© 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. 100152
    Prev
    Next
    INDEX
    Explanations

    molecular biology studies

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

    The neuron activates for the word "biology" when used in academic or 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
     exquisitely
    -2.59
     Their
    -2.53
     There
    -2.52
     psychotic
    -2.48
    哢
    -2.47
    意味着
    -2.38
     longstanding
    -2.36
     ONLY
    -2.31
     desolate
    -2.31
     […]
    -2.30
    POSITIVE LOGITS
    .
    3.70
    桖
    2.77
    7
    2.72
    ли
    2.70
    1
    2.63
    3
    2.59
     imó
    2.58
     fotografias
    2.53
    渽
    2.39
    圌
    2.36
    Activations Density 0.006%

    No Known Activations