© 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. 34-GEMMASCOPE-RES-131K
    4. 83138
    Prev
    Next
    INDEX
    Explanations

    special characters and unicode

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

    The neuron responds to numeric characters (digit tokens) wherever they appear.

    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
     which
    -1.31
     both
    -1.24
     first
    -1.24
     only
    -1.20
     or
    -1.20
     ostensibly
    -1.18
     had
    -1.17
     even
    -1.16
     very
    -1.13
     nearly
    -1.13
    POSITIVE LOGITS
     cuatro
    1.16
     insanely
    1.13
    踯
    1.11
     horrid
    1.10
    immediately
    1.08
     gruesome
    1.08
     unbelievably
    1.07
     goofy
    1.06
    extremely
    1.05
     mediocre
    1.05
    Activations Density 0.021%

    No Known Activations