© 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. 22-GEMMASCOPE-RES-131K
    7. 33134
    Prev
    Next
    INDEX
    Explanations

    expectations and thoughts

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

    This neuron detects self-reflective expressions of surprise or unexpectedness (e.g., “never thought,” “didn’t anticipate,” “who would have guessed”).

    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
     only
    -1.21
    Каждый
    -1.09
    Какой
    -1.03
    Ингредиенты
    -1.02
    ？？？
    -1.02
    𝘞
    -1.00
     both
    -0.98
     qualcuno
    -0.96
    內容簡介
    -0.96
    ᝢ
    -0.96
    POSITIVE LOGITS
     to
    1.59
     هذا
    1.28
     acht
    1.13
     шесть
    1.11
    竟然
    1.09
    如此
    1.08
    refundable
    1.08
    まさか
    1.02
     uma
    1.02
     aż
    1.02
    Activations Density 0.013%

    No Known Activations