© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73852
    Prev
    Next
    INDEX
    Explanations

    years, names, and specific entities

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

    The neuron selectively activates on numeric tokens (digits), especially when they appear as part of dates, version numbers, or legal/case identifiers.

    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
     two
    -1.64
     if
    -1.48
     If
    -1.41
     large
    -1.39
     people
    -1.38
     because
    -1.38
     should
    -1.37
     big
    -1.33
    Two
    -1.32
    "
    -1.31
    POSITIVE LOGITS
     différentes
    1.52
    และ
    1.41
     verschillende
    1.41
     différents
    1.36
    
    1.34
     magnific
    1.32
     Dinas
    1.28
     diversos
    1.27
     espesor
    1.27
     praticamente
    1.26
    Activations Density 0.002%

    No Known Activations