© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26066
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations

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

    The neuron activates on numeric tokens (integers, decimals, or symbols containing digits).

    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
     интел
    -0.93
     объясня
    -0.90
     レンタル
    -0.88
     Lidé
    -0.88
    heureusement
    -0.88
     AssertionError
    -0.86
    rapp
    -0.85
    bentuk
    -0.84
    Expense
    -0.83
    ornadas
    -0.83
    POSITIVE LOGITS
     时间
    0.98
    كتشاف
    0.87
     director
    0.83
    __':
    0.81
     företag
    0.80
    態
    0.80
    ных
    0.79
    リスク
    0.79
    руп
    0.79
     realisation
    0.79
    Activations Density 0.006%

    No Known Activations