© 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. 34-GEMMASCOPE-RES-131K
    7. 62926
    Prev
    Next
    INDEX
    Explanations

    place names and titles

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

    The main thing this neuron does is detect numeric tokens—sequences of digits (e.g. years, measurements, counts, phone numbers).

    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
    Besos
    -0.76
    persistent
    -0.73
    Gabriela
    -0.71
     Visible
    -0.71
    爭
    -0.68
    陸上
    -0.67
    visible
    -0.66
     irrelevant
    -0.66
     dormitorios
    -0.66
    Ár
    -0.66
    POSITIVE LOGITS
     Tunisia
    0.76
     Cain
    0.75
     đám
    0.74
    estructuras
    0.73
    pote
    0.72
     marrow
    0.72
    .)-
    0.71
    防控
    0.71
    gradient
    0.71
    ially
    0.71
    Activations Density 0.013%

    No Known Activations