© 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. 83187
    Prev
    Next
    INDEX
    Explanations

    Ponte or Ponto followed by various suffixes

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

    The neuron consistently fires on the letter sequence “Pont” (e.g. in “Ponte,” “Ponto,” “Pontifical,” “Pontious,” etc.), i.e. tokens containing that specific substring.

    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
    Wonderful
    -0.77
     σα
    -0.73
     zure
    -0.72
     Objects
    -0.72
    SUM
    -0.71
    ري
    -0.71
    هل
    -0.71
    Lamp
    -0.71
    oops
    -0.70
     PQ
    -0.69
    POSITIVE LOGITS
     scares
    0.80
    fract
    0.79
    逆
    0.69
    szön
    0.67
    ísmo
    0.66
    ीड
    0.65
     schemes
    0.65
     Pilate
    0.65
    亦
    0.64
     outsole
    0.64
    Activations Density 0.037%

    No Known Activations