© 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. 105721
    Prev
    Next
    INDEX
    Explanations

    1991

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

    The main thing this neuron does is find four-digit numbers representing 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_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
    0
    -2.11
    letics
    -1.81
    fficking
    -1.80
    anyahu
    -1.80
    袿
    -1.76
    outWeight
    -1.75
    ᯅ
    -1.73
    🎦
    -1.72
     inconspicuous
    -1.71
    Παρα
    -1.70
    POSITIVE LOGITS
    </td>
    2.75
    al
    2.36
    am
    2.28
    </b>
    1.97
    </sup>
    1.95
    </h2>
    1.84
     Kompon
    1.76
     [...
    1.70
    non
    1.70
    ","
    1.70
    Activations Density 0.065%

    No Known Activations