© 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. 68123
    Prev
    Next
    INDEX
    Explanations

    periods, eras, time

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

    The neuron detects references to temporal spans or periods (words like “time,” “period,” “era,” “span,” etc.).

    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
    OUTUBE
    -1.42
    according
    -1.37
     according
    -1.37
    tyard
    -1.34
    after
    -1.32
    ıdır
    -1.31
    ándor
    -1.31
    驁
    -1.30
    cellor
    -1.30
    SEGUIR
    -1.27
    POSITIVE LOGITS
    (
    1.81
     Houſe
    1.55
    ’
    1.48
     its
    1.48
    Можно
    1.39
    ِ
    1.38
    ковского
    1.30
    ين
    1.29
    hängigkeit
    1.28
    ↵
    1.27
    Activations Density 0.032%

    No Known Activations