© 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. 15215
    Prev
    Next
    INDEX
    Explanations

    FIG. or Table followed by descriptive text

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

    The neuron detects standalone numeric labels (e.g., figure or table numbers) in the text.

    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
     kollu
    -1.70
     ekip
    -1.70
    ❦
    -1.64
     短发
    -1.63
    çok
    -1.62
     Mère
    -1.62
     namens
    -1.61
     kurios
    -1.59
    “”
    -1.57
     bepa
    -1.56
    POSITIVE LOGITS
    5
    2.33
    3
    2.30
    2
    2.16
     is
    1.97
    0
    1.88
    4
    1.85
           
    1.78
     siempre
    1.78
         
    1.69
    1
    1.66
    Activations Density 0.004%

    No Known Activations