© 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. 10-GEMMASCOPE-RES-131K
    7. 43542
    Prev
    Next
    INDEX
    Explanations

    numbers in dates

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

    The neuron fires on numeric tokens—especially digits and numbers used in dates or measurements.

    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
    ),
    -1.63
     schöner
    -1.59
    ATION
    -1.52
     already
    -1.48
    媼
    -1.44
    当即
    -1.41
     dostęp
    -1.39
     bisschen
    -1.38
    开始了
    -1.38
     are
    -1.37
    POSITIVE LOGITS
     of
    1.83
    .
    1.63
     dinosau
    1.58
     Ministre
    1.56
    jų
    1.39
    錀
    1.38
    踽
    1.38
    |;
    1.38
    ỽ
    1.36
    ᾄ
    1.36
    Activations Density 0.161%

    No Known Activations