© 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. 80623
    Prev
    Next
    INDEX
    Explanations

    Numerical codes and place names

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

    The neuron activates on numeric tokens—especially multi‐digit numbers (e.g. IDs, zip codes, train numbers, dates, coordinates).

    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
     you
    -1.70
    彼女は
    -1.67
     today
    -1.60
    </h3>
    -1.47
     our
    -1.45
    dze
    -1.44
    </h5>
    -1.43
    おわりに
    -1.41
     generalmente
    -1.41
    --
    -1.41
    POSITIVE LOGITS
    3
    1.76
    These
    1.69
    1
    1.68
    this
    1.67
     Usaha
    1.64
    8
    1.53
    4
    1.52
    They
    1.52
    6
    1.52
    ään
    1.51
    Activations Density 0.077%

    No Known Activations