© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35560
    Prev
    Next
    INDEX
    Explanations

    keys to

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

    The neuron is triggered by numeric tokens, i.e. numbers and statistical figures appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    zelfde
    -1.00
    iement
    -0.94
    říve
    -0.93
    مقدمه
    -0.90
     אשר
    -0.90
    iodía
    -0.90
    illerato
    -0.88
    خدام
    -0.88
    enné
    -0.88
     kleuren
    -0.87
    POSITIVE LOGITS
     this
    1.46
     include
    0.96
     are
    0.96
     these
    0.93
     That
    0.91
     something
    0.91
    がありません
    0.91
     have
    0.91
     including
    0.88
    信心
    0.88
    Activations Density 0.017%

    No Known Activations