© 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. 47270
    Prev
    Next
    INDEX
    Explanations

    navigate through complexity

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

    The main thing this neuron does is detect occurrences of words related to “navigating” or “negotiating” (e.g., navigate, negotiate) in various forms.

    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
    inheritDoc
    -0.89
     Tala
    -0.88
    ogan
    -0.88
     ждать
    -0.82
     Sonnen
    -0.81
    ContentView
    -0.80
    ตร์
    -0.80
    ève
    -0.79
    ğe
    -0.79
    icae
    -0.77
    POSITIVE LOGITS
     navigate
    2.23
     waters
    1.73
     navigation
    1.66
     navigating
    1.63
     maze
    1.56
     navig
    1.49
    Navig
    1.48
     terrain
    1.46
    navigate
    1.45
     Navig
    1.44
    Activations Density 0.016%

    No Known Activations