© 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. 10-GEMMASCOPE-RES-131K
    7. 100708
    Prev
    Next
    INDEX
    Explanations

    version 2.0

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

    The neuron activates on decimal points in numeric tokens—i.e. version numbers or other numbers with dots.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     taką
    -1.44
     one
    -1.43
    though
    -1.38
     leggera
    -1.34
     lengths
    -1.34
    such
    -1.32
    --
    -1.30
     examples
    -1.30
     Examples
    -1.30
    目的是
    -1.29
    POSITIVE LOGITS
    viembre
    1.55
     είχε
    1.52
     $^{\
    1.52
    čiai
    1.47
     ebay
    1.45
    高級
    1.45
    ásticos
    1.41
    redientes
    1.41
     stycznia
    1.41
     inventario
    1.40
    Activations Density 0.057%

    No Known Activations