© 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. 13502
    Prev
    Next
    INDEX
    Explanations

    end of sentence after quotes

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

    The neuron strongly activates on numeric tokens (digits or 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_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
    MB
    -0.91
    UCL
    -0.88
    änien
    -0.88
    𞤢
    -0.87
    PSU
    -0.87
    cambiar
    -0.85
    Scenario
    -0.85
    Snoo
    -0.84
    mb
    -0.84
    …
    -0.83
    POSITIVE LOGITS
     tranquila
    1.16
    んだよね
    1.13
     Meksika
    1.04
     Erkrankungen
    1.03
     Symptome
    1.02
     MUNDO
    1.00
    Postup
    0.98
    感じで
    0.94
    ･･
    0.93
     cik
    0.93
    Activations Density 0.093%

    No Known Activations