© 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. 22-GEMMASCOPE-RES-131K
    7. 95830
    Prev
    Next
    INDEX
    Explanations

    percent

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

    The neuron is triggered by numerical tokens and numeric expressions (dates, years, amounts, counts) 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
    なんですよ
    -0.96
     peines
    -0.95
     ]);
    -0.94
     ank
    -0.93
    だな
    -0.92
     Descub
    -0.90
     gustaría
    -0.90
     jú
    -0.89
     Trouvez
    -0.89
     Faites
    -0.88
    POSITIVE LOGITS
     zweier
    0.91
    への
    0.89
    tions
    0.86
    ticio
    0.85
     prezzi
    0.85
    wife
    0.85
    quer
    0.85
    ⼿
    0.85
    ous
    0.84
    Biblia
    0.84
    Activations Density 0.005%

    No Known Activations