© 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. 44431
    Prev
    Next
    INDEX
    Explanations

    time durations

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

    The neuron detects cooking time expressions—mentions of durations (minutes, seconds, hours) and related timing instructions in recipes.

    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
    𖥧
    -1.61
    罔
    -1.55
    astres
    -1.55
     today
    -1.54
    
    -1.53
     destrucción
    -1.53
    変わる
    -1.51
     grandeza
    -1.51
     indivíduo
    -1.50
    嵛
    -1.50
    POSITIVE LOGITS
    .
    2.08
     if
    1.82
    There
    1.77
    ,
    1.72
    If
    1.72
    The
    1.65
    Still
    1.61
     –
    1.56
    他們
    1.55
    This
    1.53
    Activations Density 0.009%

    No Known Activations