© 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. 15659
    Prev
    Next
    INDEX
    Explanations

    words starting with dis

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

    This neuron detects the “dis-” prefix (the negation or removal prefix “dis”) at the start of words.

    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
    .
    -2.64
    事も
    -2.38
     pivotal
    -2.11
    ᨈ
    -2.09
     imaginación
    -2.06
    事で
    -2.03
     atracción
    -2.02
    ization
    -1.98
    켭
    -1.96
     tetapi
    -1.95
    POSITIVE LOGITS
    }
    2.42
    ",
    2.42
     всѣ
    2.38
     για
    2.34
     برای
    2.34
    咴
    2.31
    </h5>
    2.30
     dis
    2.25
    的说道
    2.22
    躝
    2.22
    Activations Density 0.007%

    No Known Activations