© 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. 34-GEMMASCOPE-RES-131K
    7. 6826
    Prev
    Next
    INDEX
    Explanations

    postal service wording

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

    The neuron fires on numeric tokens and other standalone identifiers—e.g. numbers, dates, codes, and URL/domain fragments.

    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
     ANZ
    -0.78
    囱
    -0.76
    استفاده
    -0.74
    Siempre
    -0.73
     Counselling
    -0.72
    Paypal
    -0.71
     MINERAL
    -0.71
    図書館
    -0.71
    hasilkan
    -0.70
    newFile
    -0.70
    POSITIVE LOGITS
     LETTER
    0.92
     Letters
    0.87
     Letter
    0.87
     letter
    0.84
     letters
    0.84
    Letter
    0.81
    LETTERS
    0.80
    letters
    0.75
     Tomb
    0.75
    andes
    0.74
    Activations Density 0.023%

    No Known Activations