© 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. 22-GEMMASCOPE-RES-131K
    7. 35928
    Prev
    Next
    INDEX
    Explanations

    math symbols and variables

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

    The neuron strongly activates on mathematical symbols denoting number sets or domains (e.g. “ℤ,” “ℝ”) and related variable notation.

    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
     said
    -1.63
     your
    -1.24
    のですか
    -1.23
     of
    -1.18
     -
    -1.17
     then
    -1.16
    ことも
    -1.14
         
    -1.14
    /*!
    -1.13
    end
    -1.13
    POSITIVE LOGITS
    がありますが
    1.50
    もありました
    1.44
    issait
    1.41
     norvég
    1.38
     auge
    1.36
     DOMINGO
    1.34
    もありますが
    1.33
     lavable
    1.33
     tristes
    1.30
    BindingResult
    1.27
    Activations Density 0.061%

    No Known Activations