© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15640
    Prev
    Next
    INDEX
    Explanations

    thoughts and opinions

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

    The neuron fires on occurrences of the word “thoughts.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    盌
    -2.38
     aktiviert
    -2.36
     Descri
    -2.25
     Specially
    -2.23
    which
    -2.19
     основных
    -2.17
     mehrere
    -2.17
    眼睛
    -2.16
    萣
    -2.16
     SEVER
    -2.14
    POSITIVE LOGITS
    .
    3.39
    犼
    2.41
    <bos>
    2.33
     ktor
    2.28
    颶
    2.20
     concise
    2.20
     even
    2.16
    輓
    2.13
    军的
    2.11
     opinions
    2.09
    Activations Density 0.006%

    No Known Activations