© 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. 16685
    Prev
    Next
    INDEX
    Explanations

    questions and code comments

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

    The neuron strongly activates on numeric literals (numbers) embedded in code.

    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
    Ār
    -1.30
    klassen
    -1.17
    loggen
    -1.15
     accepte
    -1.12
     dictadura
    -1.11
    serien
    -1.09
    -¡
    -1.09
     escuela
    -1.07
     ajoute
    -1.06
     soldado
    -1.06
    POSITIVE LOGITS
     diversa
    1.17
    /***
    1.02
    #
    1.01
    <!--
    0.99
    *
    0.99
     what
    0.97
    </i>
    0.97
     )
    0.96
    人
    0.95
    /*
    0.94
    Activations Density 0.000%

    No Known Activations