© 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. 89759
    Prev
    Next
    INDEX
    Explanations

    words starting with Whe

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

    The neuron activates on occurrences of the letter sequence “whe,” flagging tokens that begin with that substring (e.g. “Wheaton,” “Wheatstone,” “wheezing,” etc.).

    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
     坂
    -0.79
     enjoy
    -0.76
     sağlay
    -0.74
    ހ
    -0.73
     производ
    -0.73
     tega
    -0.73
    telek
    -0.71
    strict
    -0.71
     enjoyment
    -0.69
     Singles
    -0.68
    POSITIVE LOGITS
    Whe
    1.73
     Whe
    1.45
     whe
    1.31
    whe
    1.21
     WHE
    1.19
    WHE
    1.09
     whee
    0.98
     Wheel
    0.90
     wheel
    0.82
     whet
    0.79
    Activations Density 0.016%

    No Known Activations