© 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. 34-GEMMASCOPE-RES-131K
    7. 32465
    Prev
    Next
    INDEX
    Explanations

    dates and licenses

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

    The neuron strongly activates on sequences of digits (e.g. version numbers, dates, timestamps) in code comments and file headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    壓
    -0.95
     préparer
    -0.89
    autique
    -0.88
    異なります
    -0.87
     území
    -0.85
    違います
    -0.84
     inmueble
    -0.84
    里面的
    -0.84
     итоге
    -0.82
    -0.82
    POSITIVE LOGITS
     by
    0.83
     from
    0.82
    浙
    0.76
     Bloomberg
    0.76
     Ediciones
    0.75
     wri
    0.75
    Lounge
    0.74
    ')}}"
    0.73
     especí
    0.73
    倶
    0.73
    Activations Density 0.211%

    No Known Activations