© 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. 9928
    Prev
    Next
    INDEX
    Explanations

    code structure and parentheticals

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

    The neuron strongly responds to the “=)” smiley emoticon whenever it appears.

    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
    笮
    -2.67
    馀
    -2.59
    Välisling
    -2.56
     $^{\
    -2.56
    蓴
    -2.45
    荦
    -2.45
     That
    -2.42
    鳢
    -2.42
    ing
    -2.33
    鲣
    -2.33
    POSITIVE LOGITS
    If
    4.03
    1
    3.20
    It
    3.08
    –
    2.92
    9
    2.83
    2
    2.78
    8
    2.78
    4
    2.56
     It
    2.50
    A
    2.50
    Activations Density 0.001%

    No Known Activations