© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97870
    Prev
    Next
    INDEX
    Explanations

    bioactivity and biosynthesis

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

    The neuron identifies variations of the word "bio" in scientific contexts, such as "biosensors," "biological," "biomedicine," and "bioanalysis."

    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_34/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
     Punkte
    -0.73
    ностях
    -0.73
     покра
    -0.73
    rouvez
    -0.72
    CRIM
    -0.70
    ipc
    -0.69
    föl
    -0.69
     Bertram
    -0.68
     Scholz
    -0.66
     Gotta
    -0.66
    POSITIVE LOGITS
    '],
    0.76
     Pythag
    0.70
    setMin
    0.69
    灵感
    0.69
     хви
    0.68
    creas
    0.68
    too
    0.68
     Fool
    0.68
     TOO
    0.67
     processions
    0.67
    Activations Density 0.044%

    No Known Activations