© 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. 22-GEMMASCOPE-RES-131K
    7. 32828
    Prev
    Next
    INDEX
    Explanations

    locations and distances

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

    The neuron primarily detects numeric expressions, especially measurements such as distances, times, and other quantitative values.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </em>
    -1.10
     当前
    -0.93
     PyTuple
    -0.93
    waitKey
    -0.91
     sprawie
    -0.87
    HandlerContext
    -0.85
     জন্য
    -0.85
     Kriterien
    -0.85
     Stellung
    -0.84
    ebbe
    -0.82
    POSITIVE LOGITS
     distanced
    0.94
    Colore
    0.94
     schlä
    0.93
     màng
    0.93
    רְ
    0.92
     looted
    0.90
     animado
    0.90
    Segue
    0.88
    Controllo
    0.88
    Carro
    0.85
    Activations Density 0.004%

    No Known Activations