© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56810
    Prev
    Next
    INDEX
    Explanations

    color doppler

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

    This neuron fires on common discourse markers and modals—words like could, also, because, effect, and similar tokens that introduce reasoning or connect ideas.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     colonies
    -1.30
     colony
    -1.01
     Colony
    -0.89
    colony
    -0.84
     so
    -0.83
     almost
    -0.83
    까지
    -0.79
    Colony
    -0.75
     Sonic
    -0.73
    lac
    -0.71
    POSITIVE LOGITS
     hinauf
    0.91
     metas
    0.83
     Amiga
    0.81
    一直在
    0.80
     Blok
    0.80
     området
    0.79
     certamente
    0.79
     SESSION
    0.79
    hardware
    0.79
     Paket
    0.78
    Activations Density 0.016%

    No Known Activations