© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14713
    Prev
    Next
    INDEX
    Explanations

    day in context

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

    The neuron activates on numeric tokens (i.e. any standalone numbers or digits 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_22/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
    <bos>
    -0.99
     بسر
    -0.97
    <strong>
    -0.97
    这次
    -0.95
     is
    -0.93
    sige
    -0.93
    ői
    -0.91
    тын
    -0.91
    рующие
    -0.89
    </em>
    -0.89
    POSITIVE LOGITS
     day
    1.59
    結束
    1.22
     dzień
    1.08
     روزی
    1.06
    Dzień
    1.04
    day
    1.02
    那天
    0.98
    グレ
    0.98
     waarop
    0.98
     days
    0.94
    Activations Density 0.046%

    No Known Activations