© 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. 22-GEMMASCOPE-RES-131K
    7. 72820
    Prev
    Next
    INDEX
    Explanations

    dates and years

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

    The neuron fires on standalone numeric tokens, especially those forming dates or years.

    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
    ⎛
    -1.12
     that
    -1.10
     す
    -1.06
     mög
    -1.04
     what
    -1.03
    DeclareMath
    -1.02
     faço
    -1.02
    Codec
    -1.01
    </h2>
    -0.99
     existem
    -0.99
    POSITIVE LOGITS
     and
    1.33
     также
    1.26
    менты
    1.25
     akik
    1.18
    aulted
    1.13
     liars
    1.08
    จะมี
    1.07
    还有一个
    1.04
     יהיה
    1.03
     Latvian
    1.02
    Activations Density 0.002%

    No Known Activations