© 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. 84238
    Prev
    Next
    INDEX
    Explanations

    recombinant biological entities

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

    The neuron detects the word "recombinant" in scientific and biological 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
     intertw
    -2.73
     sacré
    -2.64
    aktiv
    -2.64
    ⧠
    -2.64
    am
    -2.63
    }$
    -2.61
     admon
    -2.56
     geze
    -2.56
     inextrica
    -2.50
     mangled
    -2.50
    POSITIVE LOGITS
    沇
    2.97
    ～！
    2.91
    翾
    2.75
     Also
    2.58
     nearing
    2.55
     emphasizes
    2.55
    OUTUBE
    2.55
    ↵
    2.53
    谵
    2.53
     specified
    2.52
    Activations Density 0.058%

    No Known Activations