© 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. 10-GEMMASCOPE-RES-131K
    4. 127202
    Prev
    Next
    INDEX
    Explanations

    , followed by connective words

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

    The neuron is highly responsive to numeric tokens (numbers and numeric expressions, often with their adjacent punctuation).

    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
     protože
    -2.14
     because
    -2.13
    </b>
    -1.87
    的
    -1.52
     лише
    -1.45
     becauſe
    -1.44
    </sup>
    -1.41
    .");
    -1.32
     porque
    -1.27
    &=&
    -1.27
    POSITIVE LOGITS
    ,
    1.79
    partnership
    1.46
     tzw
    1.39
    Mejores
    1.38
    </h3>
    1.38
     siquiera
    1.38
    Dữ
    1.38
    nominated
    1.34
     Перейти
    1.26
    collating
    1.26
    Activations Density 0.170%

    No Known Activations