© 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. 16483
    Prev
    Next
    INDEX
    Explanations

    legal citations and references

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

    The neuron strongly activates on multi‐digit numeric tokens (e.g. case citation numbers or patent numbers).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     délais
    -1.15
    ‘’
    -1.14
     ‘’
    -1.03
     Mereka
    -1.02
     mudanças
    -0.98
     maailman
    -0.96
     their
    -0.94
     jejich
    -0.93
    actéristi
    -0.93
    Ꮴ
    -0.93
    POSITIVE LOGITS
     only
    1.25
    lihood
    1.10
    捗
    1.02
     so
    1.01
     article
    0.99
     interface
    0.97
     before
    0.96
    lor
    0.96
     might
    0.96
     increased
    0.95
    Activations Density 0.018%

    No Known Activations