© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2101
    Prev
    Next
    INDEX
    Explanations

    Catholic hierarchy titles

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

    The neuron is keyed to biographical context, especially past‐tense “was” constructions and year or date tokens in life‐history sentences.

    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
     мати
    -0.74
    యు
    -0.73
     magnetite
    -0.73
    除去
    -0.72
    binant
    -0.69
     nodig
    -0.69
     gettin
    -0.69
     Confederation
    -0.67
    Niko
    -0.67
     ketiga
    -0.66
    POSITIVE LOGITS
     Pope
    1.23
    Pope
    1.20
     Pius
    1.04
     Apostolic
    1.03
     apostolic
    0.97
     bull
    0.94
     papal
    0.92
     pope
    0.86
     Cardinal
    0.81
     AAS
    0.80
    Activations Density 0.042%

    No Known Activations