© 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. 103399
    Prev
    Next
    INDEX
    Explanations

    Kennedy, Dynasty, Amnesty

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

    The neuron is especially sensitive to header‐style tokens—year digits, uppercase names/titles (e.g. “John,” “Kennedy”), punctuation dashes, and other metadata elements—i.e. it flags document metadata such as dates, proper names, and title text.

    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
    ․
    -0.78
    āng
    -0.76
     Hawking
    -0.76
    mêmes
    -0.75
     SqlParameter
    -0.75
    chastic
    -0.74
     {_
    -0.73
    uleiro
    -0.71
    pinMode
    -0.71
    lder
    -0.70
    POSITIVE LOGITS
     Kennedy
    1.99
     JFK
    1.98
    Kennedy
    1.80
    JFK
    1.70
     KENN
    1.42
     kenn
    1.36
     Kenn
    1.28
    Kenn
    1.03
     Came
    0.96
    迺
    0.96
    Activations Density 0.017%

    No Known Activations