© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103179
    Prev
    Next
    INDEX
    Explanations

    over the course of time

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

    The neuron detects expressions of elapsed time framed as “over the course of [time period]” (i.e. duration phrases).

    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
     and
    -2.25
     verschillen
    -2.13
    kenal
    -1.92
    抬手
    -1.88
     exclusivamente
    -1.81
     ocultar
    -1.79
    tudo
    -1.78
     It
    -1.70
    zelfde
    -1.70
     vinculado
    -1.70
    POSITIVE LOGITS
    ar
    2.44
    le
    2.36
    f
    2.34
    r
    2.28
    te
    2.28
    ll
    2.23
    rs
    2.13
    ta
    2.06
    me
    2.06
    an
    2.06
    Activations Density 0.011%

    No Known Activations