© 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. 58094
    Prev
    Next
    INDEX
    Explanations

    projector or machines

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

    The neuron detects references to copying or Xerox‐style reproduction (e.g. “xerox,” “copy,” “copying machines”).

    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
    </b>
    -2.98
     are
    -2.25
     is
    -1.88
     \
    -1.80
     you
    -1.77
    t
    -1.74
     If
    -1.74
     eigene
    -1.73
     если
    -1.73
     Of
    -1.70
    POSITIVE LOGITS
    莚
    2.70
    </h3>
    2.69
    ㆆ
    2.38
    CurtirCurtir
    2.08
     œufs
    1.95
     Perſ
    1.95
     Mitteln
    1.91
     alojamientos
    1.91
     ';
    1.89
     dibawa
    1.87
    Activations Density 0.010%

    No Known Activations