© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72502
    Prev
    Next
    INDEX
    Explanations

    HTML and code structure

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

    The neuron fires on closing delimiters—e.g. closing braces (“}”) and closing HTML/XML tags (“</…>”).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     sjuk
    -1.09
     kini
    -1.05
    Elaboración
    -1.00
     adipis
    -1.00
     относительно
    -0.97
    ának
    -0.94
     Rabu
    -0.93
    Também
    -0.92
    őség
    -0.92
    wendungs
    -0.92
    POSITIVE LOGITS
     outro
    1.12
    全体の
    1.02
    になりますが
    0.95
     program
    0.93
     идеи
    0.93
    鱷
    0.93
     weitere
    0.91
    scheduled
    0.88
     maintenir
    0.88
     concluding
    0.88
    Activations Density 0.001%

    No Known Activations