© 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. 59644
    Prev
    Next
    INDEX
    Explanations

    words starting with Ren

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

    The neuron activates on the three-letter sequence “Ren” at the start of tokens.

    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
    s
    -5.00
    鱨
    -2.95
    ی
    -2.94
    ’
    -2.88
    z
    -2.86
    뿅
    -2.81
    isieren
    -2.81
    是
    -2.72
    䛗
    -2.70
     estadounid
    -2.67
    POSITIVE LOGITS
     vendu
    2.27
     regard
    2.27
    enablog
    2.25
     rígida
    2.20
     tribute
    2.20
     Various
    2.17
     nascent
    2.17
     lament
    2.17
     prévu
    2.17
     Challenging
    2.14
    Activations Density 0.007%

    No Known Activations