© 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. 103035
    Prev
    Next
    INDEX
    Explanations

    months following a comma

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

    The neuron detects date header elements—tokens like weekday names, commas, month names, and year numbers in post metadata.

    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
     but
    -1.84
    </h2>
    -1.77
    ).
    -1.73
     العربي
    -1.66
    utilise
    -1.65
     hectáreas
    -1.65
    wendige
    -1.62
    Alguns
    -1.62
     

    -1.61
     komplette
    -1.61
    POSITIVE LOGITS
    ஂ
    2.09
     forState
    2.03
     информацию
    1.91
    ta
    1.88
    塒
    1.85
    𓋼
    1.84
    inafter
    1.83
    甞
    1.81
    us
    1.77
    ズニー
    1.74
    Activations Density 0.042%

    No Known Activations