© 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. 22-GEMMASCOPE-RES-131K
    7. 127774
    Prev
    Next
    INDEX
    Explanations

    The neuron detects invisible or zero‐width Unicode characters (e.g. byte‐order marks) embedded in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    poster, eti, am

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -1.02
     work
    -0.98
     what
    -0.98
     as
    -0.98
     mago
    -0.97
     salvador
    -0.96
    .~(\
    -0.91
     сливо
    -0.91
     lopez
    -0.91
     encompasses
    -0.90
    POSITIVE LOGITS
     воору
    0.99
     naturelles
    0.98
     elevada
    0.97
     REALLY
    0.97
     VERY
    0.96
    宬
    0.94
    really
    0.94
     conflicting
    0.94
     blatant
    0.93
     teen
    0.93
    Activations Density 0.193%

    No Known Activations