© 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. 98058
    Prev
    Next
    INDEX
    Explanations

    centered on

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

    The neuron fires on business‐oriented corporate announcements describing services or solutions, especially enterprise/security service offerings.

    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
     covid
    -2.03
    https
    -1.80
    covid
    -1.64
     LGBTQ
    -1.63
     https
    -1.63
     COVID
    -1.61
     emoji
    -1.59
    ​​​​​​​
    -1.57
    COVID
    -1.52
    ⁠
    -1.51
    POSITIVE LOGITS
     idéia
    1.71
    👊
    1.53
    😻
    1.53
    🤟
    1.48
    🤫
    1.42
    😫
    1.36
    💞
    1.35
    😩
    1.31
    myspace
    1.31
    iPod
    1.31
    Activations Density 0.256%

    No Known Activations