© 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. 10-GEMMASCOPE-RES-131K
    4. 118830
    Prev
    Next
    INDEX
    Explanations

    identifier or field name

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

    function or method names in programming code, particularly those that follow camelCase naming conventions with "By" or similar prepositions.

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

    The neuron looks for programming identifiers (especially CamelCase or TitleCase names) in code.

    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
     when
    -1.43
     quando
    -1.32
     for
    -1.32
    alucía
    -1.24
      
    -1.23
     were
    -1.19
     nachdem
    -1.19
    romeda
    -1.18
     dopo
    -1.17
     would
    -1.14
    POSITIVE LOGITS
     that
    1.87
     such
    1.80
     soulign
    1.45
     např
    1.42
     mérit
    1.39
     verdaderamente
    1.38
     espesor
    1.34
     vendu
    1.33
     acheté
    1.32
     commandé
    1.32
    Activations Density 0.057%

    No Known Activations