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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68691
    Prev
    Next
    INDEX
    Explanations

    lists of

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

    The neuron is strongly activating on very frequent function words (common English articles, prepositions, conjunctions, etc.).

    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
    抿
    -0.98
    ube
    -0.91
     pourront
    -0.88
    polation
    -0.88
     znaczy
    -0.87
     promouvoir
    -0.85
     nejen
    -0.85
    吓得
    -0.84
    ton
    -0.83
     можна
    -0.83
    POSITIVE LOGITS
    如果是
    1.15
     particularly
    0.93
     einem
    0.90
     einer
    0.88
     более
    0.85
    涉及
    0.84
     FOR
    0.83
     Armee
    0.83
     有
    0.82
     involves
    0.82
    Activations Density 0.093%

    No Known Activations