© 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. 83746
    Prev
    Next
    INDEX
    Explanations

    integral part of

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

    The neuron flags occurrences of the phrase “integral part of.”

    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
     a
    -1.87
    </i>
    -1.73
    ',
    -1.70
    </th>
    -1.46
     unwilling
    -1.44
     dicono
    -1.44
    ]$.
    -1.43
    ",
    -1.43
     umgangssprach
    -1.41
     insanların
    -1.38
    POSITIVE LOGITS
     it
    1.80
    搅
    1.73
     respective
    1.63
     raha
    1.63
    COHOL
    1.62
     descuentos
    1.59
     iep
    1.55
     amat
    1.54
    k
    1.54
    compañ
    1.52
    Activations Density 0.008%

    No Known Activations