© 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. 22-GEMMASCOPE-RES-131K
    7. 65137
    Prev
    Next
    INDEX
    Explanations

    has been a while

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

    The neuron specializes in spotting numeric expressions denoting time intervals or counts (e.g. hours, weeks, days, seasons).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    それが
    -0.95
    最後は
    -0.93
    ніе
    -0.91
     también
    -0.91
     även
    -0.91
    本当は
    -0.91
     Studies
    -0.88
     också
    -0.84
    最后的
    -0.84
     damaligen
    -0.83
    POSITIVE LOGITS
     already
    2.66
     still
    2.19
    Already
    2.08
    already
    1.98
     уже
    1.85
     Already
    1.80
     już
    1.78
     вже
    1.77
    still
    1.66
     כבר
    1.66
    Activations Density 0.063%

    No Known Activations