© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49090
    Prev
    Next
    INDEX
    Explanations

    orbits and inclination

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

    The neuron strongly activates on numeric expressions—digits, measurements, dates, angles, counts—i.e. quantitative tokens conveying quantities.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     zás
    -0.73
    goog
    -0.73
     stanie
    -0.72
    jih
    -0.71
    $-.
    -0.71
    Czy
    -0.70
     conflicto
    -0.70
     descarga
    -0.68
    ствовал
    -0.68
    pasang
    -0.67
    POSITIVE LOGITS
     inclined
    0.91
     orbit
    0.89
     Keb
    0.86
     path
    0.86
     inclination
    0.85
     ellipse
    0.79
     新作
    0.77
    setPath
    0.77
     plane
    0.76
    bulaire
    0.75
    Activations Density 0.026%

    No Known Activations