© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108818
    Prev
    Next
    INDEX
    Explanations

    finding minimum values

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

    The neuron is detecting numeric tokens (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
     maximizing
    -1.36
     maximize
    -1.36
    max
    -1.34
     maximized
    -1.34
     максима
    -1.34
    Maxim
    -1.30
    Max
    -1.30
     maximization
    -1.30
     Maxim
    -1.28
     maxillary
    -1.28
    POSITIVE LOGITS
     minimum
    3.95
     lowest
    3.41
    minimum
    3.20
    最小
    3.08
    Minimum
    3.05
     Minimum
    3.00
    lowest
    2.83
     smallest
    2.72
     min
    2.67
     mínimo
    2.66
    Activations Density 0.051%

    No Known Activations