© 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. 10-GEMMASCOPE-RES-131K
    7. 11425
    Prev
    Next
    INDEX
    Explanations

    setting object id

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

    The neuron primarily picks out numeric literals (including integers and decimals) embedded 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_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
    \
    -2.97
    _{
    -2.91
     {
    -2.63
     
    -2.50
     be
    -2.48
    ↵
    -2.47
    g
    -2.41
    4
    -2.20
    1
    -2.20
    -2.20
    POSITIVE LOGITS
    2.41
    鼙
    2.39
    //////////////
    2.31
    čkou
    2.30
     patrie
    2.30
    помним
    2.23
     arbeta
    2.22
    ين
    2.22
     MessageBoxIcon
    2.22
    💌
    2.20
    Activations Density 0.000%

    No Known Activations