© 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. 62572
    Prev
    Next
    INDEX
    Explanations

    Virgin, Branson, joined Pentagram, Q:

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

    The neuron strongly activates on title-case and proper-noun tokens (i.e. capitalized words such as names, headings, or other named entities).

    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
    utorial
    -0.85
    pok
    -0.83
     ipsum
    -0.75
    Rae
    -0.75
    addHandler
    -0.74
     Pless
    -0.74
    ccccccc
    -0.73
     Krum
    -0.73
    bnb
    -0.73
    槁
    -0.73
    POSITIVE LOGITS
     Virgin
    2.70
    Virgin
    2.34
     Branson
    2.19
     virgin
    1.80
    virgin
    1.72
     virgins
    1.59
     Richard
    1.59
    Richard
    1.50
     virginity
    1.41
     Sir
    1.31
    Activations Density 0.020%

    No Known Activations