© 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. 105748
    Prev
    Next
    INDEX
    Explanations

    dates from various languages

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

    The neuron detects numeric tokens—digits and numbers (years, dates, decimals, etc.) 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_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
    3
    -2.81
    6
    -2.33
    2
    -2.30
    4
    -2.30
    8
    -2.23
    5
    -2.13
    7
    -1.98
    1
    -1.91
     from
    -1.88
     with
    -1.81
    POSITIVE LOGITS
     umy
    1.92
     dekol
    1.74
     tajem
    1.62
     farba
    1.61
    guantes
    1.60
     znam
    1.59
    elektron
    1.58
     pude
    1.58
     noté
    1.58
     ryb
    1.57
    Activations Density 0.013%

    No Known Activations