© 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. 93170
    Prev
    Next
    INDEX
    Explanations

    headings and questions

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

    The neuron fires on multi-digit numerical values (particularly larger numbers like “108” and “140”).

    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
     ilgi
    -1.03
     this
    -1.02
     that
    -1.02
     specifik
    -0.93
     lú
    -0.89
     both
    -0.89
     viewWillAppear
    -0.87
    የ
    -0.87
    Dış
    -0.86
     DataGridView
    -0.86
    POSITIVE LOGITS
     finally
    0.95
     verschiedener
    0.87
     diversos
    0.86
     [
    0.86
     Komponenten
    0.85
    객
    0.85
    ワンピース
    0.84
     threats
    0.83
     lastly
    0.83
     Anwendungen
    0.82
    Activations Density 0.000%

    No Known Activations