© 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. 34-GEMMASCOPE-RES-131K
    7. 12063
    Prev
    Next
    INDEX
    Explanations

    if

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

    The neuron is strongly activated by numeric literals (standalone numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     renkli
    -0.96
     bisous
    -0.95
     oscura
    -0.94
     Lehrer
    -0.90
     знаете
    -0.88
    ämie
    -0.88
    外面
    -0.88
     ngayon
    -0.88
    Глава
    -0.87
     Acosta
    -0.86
    POSITIVE LOGITS
    if
    1.00
    InMillis
    0.98
    owań
    0.91
    で
    0.91
    これも
    0.90
    derd
    0.88
     Forderung
    0.86
     Betrachtung
    0.86
    issippi
    0.85
     Forderungen
    0.85
    Activations Density 0.008%

    No Known Activations