© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75246
    Prev
    Next
    INDEX
    Explanations

    daily, weekly, or seasonal activities

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

    The neuron detects temporal frequency expressions—phrases that specify how often something happens (e.g. “every day,” “once a week,” “weekends,” 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
     necesitaba
    -1.38
     quería
    -1.38
     recuer
    -1.30
    喈
    -1.27
     mereka
    -1.22
    indrops
    -1.22
    Doktor
    -1.21
     habia
    -1.21
     avantaj
    -1.21
    ੲ
    -1.20
    POSITIVE LOGITS
     to
    2.33
     into
    1.37
    d
    1.35
     jego
    1.18
    i
    1.15
    c
    1.14
     wenigstens
    1.12
     different
    1.12
    different
    1.07
    ia
    1.05
    Activations Density 0.038%

    No Known Activations