© 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. 86110
    Prev
    Next
    INDEX
    Explanations

    years in legal contexts

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

    The main thing this neuron does is detect numeric tokens (multi‐digit numbers such as years, dates, and counts).

    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
     more
    -1.68
     every
    -1.49
     other
    -1.45
     började
    -1.41
     even
    -1.38
    Приготовление
    -1.33
     принад
    -1.29
    ׇ
    -1.28
     nascita
    -1.27
     skrev
    -1.26
    POSITIVE LOGITS
     –
    1.63
     ausger
    1.61
     “
    1.48
    別の
    1.48
    <blockquote>
    1.45
    του
    1.44
    </tfoot>
    1.41
     também
    1.38
     then
    1.37
     что
    1.37
    Activations Density 0.061%

    No Known Activations