© 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. 113328
    Prev
    Next
    INDEX
    Explanations

    hetero- prefix

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

    This neuron detects scientific terms related to molecular structures that contain "hetero" prefixes, particularly heterodimers and heterozygotes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of the prefix “hetero-” in scientific or technical terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    đầm
    -2.09
    薆
    -2.06
    說
    -2.05
     guru
    -1.99
    для
    -1.97
    犼
    -1.91
    ↵↵
    -1.88
    茕
    -1.87
    퐼
    -1.84
    fél
    -1.84
    POSITIVE LOGITS
     the
    2.45
     you
    2.11
    and
    2.06
    𝙒
    1.94
    炖
    1.85
     and
    1.82
    anueva
    1.77
    {
    1.77
    跛
    1.75
    릭터
    1.73
    Activations Density 0.021%

    No Known Activations