© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116634
    Prev
    Next
    INDEX
    Explanations

    National Register of Historic Places

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

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

    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
    月号
    -0.73
    утбо
    -0.71
    ۳۰
    -0.70
     folgte
    -0.65
    rounds
    -0.65
     fatt
    -0.65
    ֽ
    -0.63
    хнет
    -0.62
    tafogo
    -0.60
    Mrs
    -0.60
    POSITIVE LOGITS
     συν
    0.71
     Identification
    0.69
    ㅘ
    0.68
    świ
    0.67
     zealand
    0.66
    aluminium
    0.65
    hehe
    0.65
    widgets
    0.65
     XS
    0.65
     EYE
    0.64
    Activations Density 0.047%

    No Known Activations