© 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. 10970
    Prev
    Next
    INDEX
    Explanations

    country music singer

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

    The neuron fires on out-of-context formatting or metadata tokens—things like standalone uppercase words or letters, isolated numbers, and stray punctuation marks.

    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
    議院
    -1.03
     APPELLATE
    -1.01
    бычно
    -0.98
    .‏
    -0.97
    кобрита
    -0.93
    //.
    -0.91
    NameExpr
    -0.91
    岀
    -0.90
    agricultural
    -0.88
    immortal
    -0.88
    POSITIVE LOGITS
     fortemente
    1.05
     discarded
    1.03
     escolher
    1.03
     frequenza
    1.02
     pertanto
    1.02
     certamente
    0.99
     понравился
    0.94
     fechar
    0.93
     executar
    0.92
    adura
    0.90
    Activations Density 0.002%

    No Known Activations