© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6337
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on long numeric strings (four‐digit and above) typical of academic citation identifiers (e.g. years, volume(issue):page numbers) in reference lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.55
    ()
    0.48
        
    0.47
      
    0.46
    }
    0.46
    <unused60>
    0.46
    0.46
       
    0.45
            
    0.45
    <0x0D>
    0.44
    POSITIVE LOGITS
    équipement
    0.48
     रक्षाबंधनाच्या
    0.45
    inairement
    0.45
    विषयी
    0.42
     جوړونکو
    0.41
     अल्को
    0.41
     بیاکتنې
    0.41
     करण्या
    0.41
     శరీ
    0.41
     निजामाच्या
    0.41
    Activations Density 0.000%

    No Known Activations