© 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. 9365
    Prev
    Next
    INDEX
    Explanations

    a domain name

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

    The neuron responds most strongly to very short tokens—especially quotation marks and common one-, two-, or three-letter function words.

    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
     richiede
    -0.94
    écri
    -0.94
     généralement
    -0.91
    ブログ村
    -0.90
     Texto
    -0.89
     Descargar
    -0.88
     bénévol
    -0.88
    decreasing
    -0.86
    indépendance
    -0.85
    臯
    -0.85
    POSITIVE LOGITS
     for
    0.85
     &
    0.82
     
    0.82
     και
    0.77
     الأعمال
    0.73
    .
    0.72
     és
    0.71
    0.71
    вшие
    0.70
     skall
    0.69
    Activations Density 0.234%
    No Known Activations