© 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. 57594
    Prev
    Next
    INDEX
    Explanations

    Historic Places

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

    This neuron detects mentions of the “National Register of Historic Places” designation.

    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
     Punkt
    -0.69
     kerajaan
    -0.68
    amat
    -0.66
    фо
    -0.63
     Softball
    -0.62
    cfg
    -0.62
     ca
    -0.62
     Offensive
    -0.61
     cellspacing
    -0.61
     والم
    -0.61
    POSITIVE LOGITS
    ión
    0.79
    東方
    0.76
    nières
    0.71
    τικού
    0.70
    ヮ
    0.69
    xil
    0.69
    arelli
    0.68
     fuite
    0.68
     mời
    0.68
     выращи
    0.67
    Activations Density 0.076%

    No Known Activations