© 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. 3129
    Prev
    Next
    INDEX
    Explanations

    SQL WHERE clauses

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

    The neuron fires on numeric literals (tokens consisting of numbers) in code or config files.

    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
     like
    -1.15
    -1.02
     seems
    -1.02
     from
    -0.97
     Seems
    -0.95
     seemed
    -0.90
    第九
    -0.90
    qquad
    -0.85
     most
    -0.84
    ĵ
    -0.82
    POSITIVE LOGITS
        
    2.53
    7
    1.12
         
    1.11
       
    1.09
    1.01
     DMSO
    0.94
      
    0.91
     SEVEN
    0.89
    Bord
    0.84
    یرات
    0.82
    Activations Density 0.110%

    No Known Activations