© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25969
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and types

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

    This neuron responds to standalone tokens that begin with an uppercase letter (i.e. capitalized identifiers or class‐style names).

    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
     they
    -1.48
     mû
    -1.45
     moletom
    -1.41
     attente
    -1.38
     sés
    -1.33
     cóc
    -1.30
     Сі
    -1.29
    already
    -1.29
     especias
    -1.29
    Fonto
    -1.26
    POSITIVE LOGITS
    名
    1.23
              
    1.21
    <strong>
    1.19
     is
    1.19
          
    1.19
     if
    1.17
    社
    1.11
                
    1.09
    需要
    1.09
           
    1.06
    Activations Density 0.002%

    No Known Activations