© 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. 68709
    Prev
    Next
    INDEX
    Explanations

    journal citations and legal references

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

    The neuron is tuned to pick up the abbreviation “App” as used in legal citations (e.g. “Ill. App.”).

    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
     такими
    -1.88
     füh
    -1.80
     bedeut
    -1.77
     utilizando
    -1.74
     pivotal
    -1.70
     refiere
    -1.67
     adept
    -1.65
     städ
    -1.64
     --
    -1.63
     VERY
    -1.63
    POSITIVE LOGITS
    ¡¡
    2.17
     ¡¡
    1.99
     hiver
    1.84
     dage
    1.83
     themſelves
    1.82
     dagen
    1.81
     Singapur
    1.80
     capot
    1.78
     vader
    1.77
    🔹
    1.77
    Activations Density 0.003%

    No Known Activations