© 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. 10-GEMMASCOPE-RES-131K
    7. 128851
    Prev
    Next
    INDEX
    Explanations

    symbols and abbreviations

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

    The neuron fires on emoji characters (e.g. 👍, 👆, 🙌, 👎, 👉) in 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_10/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
     to
    -2.77
    𖤣
    -2.20
    ありました
    -2.17
     tratando
    -2.17
     estando
    -2.13
    ↑↑↑</
    -2.06
    嬲
    -2.05
    蚺
    -2.03
    VIATIONS
    -1.99
     dejando
    -1.98
    POSITIVE LOGITS
    ?"
    2.88
    They
    2.80
    硨
    2.78
    It
    2.66
    Its
    2.66
    And
    2.63
    ="
    2.56
    𖣘
    2.53
    莯
    2.48
    replyreport
    2.47
    Activations Density 0.002%

    No Known Activations