© 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. 107243
    Prev
    Next
    INDEX
    Explanations

    hetero- prefix

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

    The neuron detects the prefix "heter" in scientific terms like "heterogeneity," "heterotopic," "heterochromatic," and other specialized technical vocabulary.

    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
     weib
    -0.82
     不可
    -0.75
    这么多
    -0.75
    思います
    -0.72
     ftate
    -0.71
    prm
    -0.69
    ISSUES
    -0.69
     Provinz
    -0.68
    应对
    -0.68
     fuper
    -0.67
    POSITIVE LOGITS
     heter
    1.15
     Heter
    1.14
     أغسطس
    0.92
    Heter
    0.91
    一直
    0.90
     Het
    0.90
     Hetero
    0.88
    Het
    0.78
    ผม
    0.76
    heizung
    0.76
    Activations Density 0.040%

    No Known Activations