© 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. 90735
    Prev
    Next
    INDEX
    Explanations

    operating business, agreements

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

    The neuron is detecting numeric tokens and number-like identifiers (digits, part numbers, dates, codes) in the document.

    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
     occaf
    -0.84
    Tutor
    -0.84
     Einwohner
    -0.83
     Institu
    -0.76
     paralle
    -0.74
    SOCIAL
    -0.72
    besitzer
    -0.72
     Instance
    -0.71
     просто
    -0.71
    🏓
    -0.71
    POSITIVE LOGITS
    引き続き
    0.96
    :
    0.86
     wahr
    0.79
    paedia
    0.78
    gaz
    0.77
     redacción
    0.77
     competitivos
    0.77
    疊
    0.77
     bienestar
    0.77
     הר
    0.77
    Activations Density 0.007%

    No Known Activations