© 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. 10-GEMMASCOPE-RES-131K
    7. 112503
    Prev
    Next
    INDEX
    Explanations

    copyright notice

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

    This neuron detects source‐file header metadata in code—especially filenames with extensions and related include‐guard or file‐name comment lines.

    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
    italien
    -1.93
     delicado
    -1.89
     gömlek
    -1.71
     yelek
    -1.67
     pantolon
    -1.67
     our
    -1.58
     ayakkabı
    -1.58
    پول
    -1.57
    badan
    -1.55
     münchen
    -1.55
    POSITIVE LOGITS
     and
    2.02
    titial
    1.68
       
    1.58
     to
    1.58
    .,
    1.55
         
    1.53
              
    1.51
     \
    1.50
                        
    1.49
      
    1.48
    Activations Density 0.069%

    No Known Activations