© 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. 34-GEMMASCOPE-RES-131K
    7. 107037
    Prev
    Next
    INDEX
    Explanations

    legal citations and numbers

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

    The neuron fires on the start of a C‐style comment delimiter (“/*”).

    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
     widespread
    -0.90
     only
    -0.89
     during
    -0.89
     determining
    -0.89
    paroles
    -0.84
    ﹎
    -0.84
    jną
    -0.84
     while
    -0.83
     when
    -0.83
    ریق
    -0.82
    POSITIVE LOGITS
                
    0.88
     smoothies
    0.85
          
    0.84
                                   
    0.82
                                  
    0.82
     และ
    0.81
                 
    0.81
    ONS
    0.80
    asim
    0.79
    ALTY
    0.79
    Activations Density 0.001%

    No Known Activations