© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40145
    Prev
    Next
    INDEX
    Explanations

    names and dates

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

    The neuron activates on tokens that consist of numeric values (e.g. years, dates, or other numbers).

    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
    رحلة
    -1.16
    During
    -1.10
     During
    -1.01
     zimní
    -0.98
    Throughout
    -0.96
     הם
    -0.94
     iy
    -0.94
    ыз
    -0.93
    Without
    -0.93
     entren
    -0.91
    POSITIVE LOGITS
    髕
    1.02
    らなかった
    0.98
    菒
    0.98
     कीजिए
    0.97
     gewerb
    0.97
     sociala
    0.96
     sostiene
    0.96
     egenskaper
    0.94
     manifestly
    0.94
     پرداز
    0.93
    Activations Density 0.561%

    No Known Activations