© 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. 128290
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of time intervals or durations (e.g. hours, minutes, days, weeks) often alongside numeric values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    time intervals and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     by
    -0.98
    ranton
    -0.94
    istorante
    -0.93
    ียบ
    -0.92
     laterales
    -0.92
     adjunto
    -0.89
     marido
    -0.89
    utuhan
    -0.89
     longtime
    -0.88
     sguardo
    -0.88
    POSITIVE LOGITS
    -------
    0.95
    each
    0.90
    rália
    0.89
    Volunteers
    0.88
    ane
    0.88
    every
    0.86
     until
    0.86
    tham
    0.85
    teens
    0.85
     weeks
    0.85
    Activations Density 0.052%

    No Known Activations