© 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. 22-GEMMASCOPE-RES-131K
    7. 70828
    Prev
    Next
    INDEX
    Explanations

    coincidence, uncanny connections

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

    The neuron fires on informal, fan-style comments addressing the author directly—especially excited praise or “you have a new fan”–type messages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    llons
    -1.00
    ရ
    -0.92
    ostock
    -0.92
    ULAS
    -0.92
    别
    -0.92
    桂
    -0.88
     sev
    -0.86
    ylate
    -0.85
    ulas
    -0.85
    :^(
    -0.84
    POSITIVE LOGITS
     coincidence
    2.36
     coinc
    1.70
     coincident
    1.46
     coinciden
    1.39
     сов
    1.35
     coincid
    1.16
    偶然
    1.15
    剛好
    1.10
     uncanny
    1.08
     connection
    1.06
    Activations Density 0.057%

    No Known Activations