© 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. 39613
    Prev
    Next
    INDEX
    Explanations

    till a point in time

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

    The neuron activates on tokens that represent numeric or temporal expressions (numbers, dates, “till,” 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
    ↵↵
    -1.67
     dessas
    -1.60
    剮
    -1.48
     happened
    -1.40
    .'
    -1.40
     dieser
    -1.39
    铪
    -1.38
    ทั้ง
    -1.37
     Trivia
    -1.35
    菝
    -1.33
    POSITIVE LOGITS
     this
    2.05
     the
    1.74
     freundlichen
    1.61
     which
    1.56
     kağıdı
    1.47
    ﹍﹍
    1.45
    了你
    1.45
     it
    1.42
     that
    1.40
    ientras
    1.40
    Activations Density 0.032%

    No Known Activations