© 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. 50429
    Prev
    Next
    INDEX
    Explanations

    WITHOUT WARRANTY, Corporation Counsel

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

    The neuron activates on numeric tokens (numbers).

    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
     hallucinations
    -0.74
     NEWSLETTER
    -0.65
     commandments
    -0.64
    スタンダ
    -0.64
    Plus
    -0.63
    允许
    -0.63
     பொ
    -0.63
     Alden
    -0.62
    wingen
    -0.62
    onso
    -0.62
    POSITIVE LOGITS
     користу
    0.75
    edx
    0.67
    iffer
    0.67
     runtime
    0.66
    latform
    0.65
    addMouseListener
    0.63
    MAPPING
    0.63
     Francesca
    0.63
    continent
    0.62
    astype
    0.61
    Activations Density 0.077%

    No Known Activations