© 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. 68170
    Prev
    Next
    INDEX
    Explanations

    recently,

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

    This neuron fires on the temporal discourse marker “Recently,” at the start of a new statement.

    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
    -1.86
    <td>
    -1.71
    ffed
    -1.55
     owe
    -1.50
    {
    -1.50
    nyi
    -1.46
    giène
    -1.46
    ICOLON
    -1.46
     if
    -1.45
    眼底
    -1.45
    POSITIVE LOGITS
    𞤢
    1.87
    ーズン
    1.64
    ズニー
    1.64
     spectateurs
    1.62
    話は
    1.58
    期间
    1.57
    3
    1.55
    瑨
    1.55
    1
    1.55
    晅
    1.54
    Activations Density 0.025%

    No Known Activations