© 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. 32857
    Prev
    Next
    INDEX
    Explanations

    code and foreign words

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

    The neuron is triggered by numeric literal tokens (e.g. standalone numbers) embedded in code or configuration files.

    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
     chitar
    -1.02
    ⭐️
    -0.99
    viève
    -0.93
     userRepository
    -0.91
    poin
    -0.89
     portugués
    -0.89
    kunjung
    -0.89
    ,$_
    -0.88
    rupted
    -0.88
     produs
    -0.88
    POSITIVE LOGITS
    gento
    0.96
     нарушение
    0.90
    Braun
    0.90
     liées
    0.87
     jego
    0.86
     réuss
    0.85
     erreur
    0.84
     ajouter
    0.83
     know
    0.83
     fått
    0.82
    Activations Density 0.013%

    No Known Activations