© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103238
    Prev
    Next
    INDEX
    Explanations

    phone numbers and country codes

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

    The neuron specifically fires on the use of parentheses (i.e. “(” and “)”) around numeric or reference information.

    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
    さてさて
    -1.45
    さぁ
    -1.41
    錾
    -1.41
     because
    -1.41
     ненави
    -1.38
    ではでは
    -1.34
    Воспита
    -1.33
     nasze
    -1.32
     時
    -1.31
     lavable
    -1.31
    POSITIVE LOGITS
     to
    1.73
     harten
    1.35
    tığı
    1.32
     spannende
    1.31
     actualmente
    1.30
    changers
    1.25
     
    1.24
    沅
    1.21
     ofrecen
    1.21
     and
    1.20
    Activations Density 0.003%

    No Known Activations