© 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. 10-GEMMASCOPE-RES-131K
    7. 119550
    Prev
    Next
    INDEX
    Explanations

    java code keywords

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

    variable names in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on tokens that contain digits (i.e. numeric literals and numbers).

    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
    。</
    -1.45
    zensionen
    -1.38
     capitulo
    -1.35
    zijde
    -1.31
     your
    -1.28
     during
    -1.27
     one
    -1.23
    蒹
    -1.22
     Semoga
    -1.22
     menetap
    -1.14
    POSITIVE LOGITS
     –
    1.77
    -
    1.60
     STILL
    1.30
               
    1.30
     dormitórios
    1.25
    ’
    1.23
     -
    1.21
     was
    1.21
                  
    1.21
          
    1.21
    Activations Density 0.002%

    No Known Activations