© 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. 54260
    Prev
    Next
    INDEX
    Explanations

    re-use and repurpose

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

    The neuron detects occurrences of the substring “re” as a prefix or embedded morpheme (e.g. in re-use, reconfigure, repurpose).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    oudou
    -0.83
    ksesta
    -0.77
    нитар
    -0.74
    人了
    -0.72
    utados
    -0.72
     ഒരു
    -0.71
    icias
    -0.70
    יצוני
    -0.70
    اعده
    -0.69
    Somos
    -0.69
    POSITIVE LOGITS
     use
    2.92
    Use
    2.53
    use
    2.48
     Use
    2.28
     usage
    2.20
     استفاده
    1.94
     uses
    1.91
    USE
    1.89
     использования
    1.85
     उपयोग
    1.84
    Activations Density 0.036%

    No Known Activations