© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58583
    Prev
    Next
    INDEX
    Explanations

    numerical degree measurements

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

    This neuron detects geographic coordinate notation, especially degree symbols and related latitude/longitude markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    they
    -1.98
    They
    -1.74
     particularly
    -1.61
    itemize
    -1.61
     says
    -1.61
    ってみて
    -1.60
     épo
    -1.59
     dureza
    -1.59
     válvula
    -1.58
    there
    -1.56
    POSITIVE LOGITS
     of
    1.72
    氿
    1.52
    <td>
    1.51
    traueranzeige
    1.51
     Tidak
    1.47
     неболь
    1.46
    箒
    1.46
    казания
    1.45
     география
    1.43
     på
    1.41
    Activations Density 0.002%

    No Known Activations