© 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. 34-GEMMASCOPE-RES-131K
    7. 31455
    Prev
    Next
    INDEX
    Explanations

    year-round

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

    The neuron activates on temporal phrases indicating continuous, year-long (year-round or year-long) durations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    日目
    -0.81
     mientras
    -0.78
     после
    -0.77
     zuletzt
    -0.77
     लाख
    -0.77
     вместе
    -0.76
     meinem
    -0.74
     uiteindelijk
    -0.73
     isComment
    -0.72
    iph
    -0.71
    POSITIVE LOGITS
     year
    5.53
    year
    3.44
     YEAR
    3.34
    Year
    3.27
     året
    3.20
     Year
    3.11
     año
    2.77
    YEAR
    2.77
    année
    2.67
    一年
    2.66
    Activations Density 0.096%

    No Known Activations