© 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. 39798
    Prev
    Next
    INDEX
    Explanations

    "At", "Organic", "Q", "The", "Shay" followed by names

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

    The neuron activates on HTML superscript tags (i.e. “<sup>”).

    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
    籐
    -2.63
    。」
    -2.48
     includes
    -2.45
     Several
    -2.38
     For
    -2.33
     TWO
    -2.33
     or
    -2.31
     in
    -2.31
    逡
    -2.28
     swiftly
    -2.25
    POSITIVE LOGITS
    {
    4.19
    <
    3.14
    </strong>
    2.81
     magnificent
    2.80
     astonishing
    2.77
     bizarre
    2.66
     marvelous
    2.63
    IN
    2.61
     magnific
    2.55
    那你
    2.50
    Activations Density 0.000%

    No Known Activations