© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87240
    Prev
    Next
    INDEX
    Explanations

    words starting with Re

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

    The neuron strongly activates on the “Re” prefix used in message‐ or email‐style reply headers.

    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
    m
    -3.16
    "
    -2.98
    },
    -2.84
     oder
    -2.77
    .
    -2.56
    \
    -2.53
    st
    -2.52
    cu
    -2.50
    ac
    -2.48
     și
    -2.48
    POSITIVE LOGITS
    Ꭳ
    2.78
    îné
    2.77
    begin
    2.69
     Regret
    2.66
    酲
    2.58
     古风
    2.56
    ญี่ป
    2.55
     การ์ตูน
    2.48
     Considered
    2.47
    zelfde
    2.45
    Activations Density 0.011%

    No Known Activations