© 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. 34-GEMMASCOPE-RES-131K
    7. 62406
    Prev
    Next
    INDEX
    Explanations

    about this/the [content type]

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

    The neuron strongly activates on the word “this,” especially when it appears in section headings like “About this ….”

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Mfg
    -0.85
    Pgina
    -0.82
    newList
    -0.82
    Helmut
    -0.79
    Abhi
    -0.74
    Lucie
    -0.72
     krä
    -0.71
    Vitals
    -0.71
    Gabe
    -0.70
    conductivity
    -0.70
    POSITIVE LOGITS
     woning
    0.84
    Villa
    0.70
    voca
    0.70
    HasMaxLength
    0.69
    quer
    0.69
     content
    0.68
    词汇
    0.68
    integer
    0.68
    Scheme
    0.67
     hidup
    0.67
    Activations Density 0.057%

    No Known Activations