© 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. 67665
    Prev
    Next
    INDEX
    Explanations

    years between 1957 and 2016

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

    The neuron detects four-digit numeric tokens representing years (date references) in the text.

    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
     the
    -1.56
     Tropfen
    -1.27
    sempre
    -1.25
    increases
    -1.21
     Zustand
    -1.17
     récemment
    -1.16
     csomag
    -1.16
    seemed
    -1.14
    troppo
    -1.13
     USED
    -1.13
    POSITIVE LOGITS
     have
    1.52
     started
    1.27
     to
    1.27
    ?
    1.24
     также
    1.23
    šn
    1.19
     didn
    1.18
    ৄ
    1.18
     chose
    1.17
    setTimestamp
    1.17
    Activations Density 0.112%

    No Known Activations