© 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. 106853
    Prev
    Next
    INDEX
    Explanations

    United States

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

    The neuron strongly activates on numeric tokens representing years (e.g. “2017,” “2018”) in copyright or license headers.

    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
    öglich
    -0.73
    postMessage
    -0.71
    titure
    -0.71
     jot
    -0.71
     într
    -0.69
    SANTA
    -0.67
    assertSame
    -0.66
     הני
    -0.66
    Jwt
    -0.66
    isko
    -0.66
    POSITIVE LOGITS
     Braid
    0.79
    pillars
    0.79
    anso
    0.77
     pysty
    0.77
    日的
    0.76
     tehd
    0.75
    irvana
    0.71
    imagining
    0.69
    hike
    0.69
    ثة
    0.69
    Activations Density 0.150%

    No Known Activations