© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5082
    Prev
    Next
    INDEX
    Explanations

    PowerPoint presentation

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

    The neuron is picking out large multi‐sentence blocks or paragraph/quote boundaries—i.e. the start of long uninterrupted text segments.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
      
    0.77
    onycha
    0.52
     Sainsbury
    0.49
    කාර
    0.49
     tiver
    0.48
     Coolidge
    0.48
     Might
    0.48
     admixture
    0.48
    ருக்கும்
    0.47
     might
    0.47
    POSITIVE LOGITS
     "
    0.80
    -"
    0.78
    bibliography
    0.75
     -"
    0.73
     "¿
    0.72
    ​
    0.71
    "]]
    0.71
    "
    0.71
    ("
    0.69
    ."
    0.67
    Activations Density 0.060%

    No Known Activations