© 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. 34-GEMMASCOPE-RES-131K
    7. 58551
    Prev
    Next
    INDEX
    Explanations

    URL encoding, special characters

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

    The neuron activates on tokens containing numeric characters—e.g. digits in numbers, percent-codes, or HTML numeric entities.

    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
     unique
    -1.20
     būt
    -0.99
     which
    -0.99
     so
    -0.97
    お楽しみに
    -0.96
    Tazama
    -0.94
    Satu
    -0.93
     phenomenal
    -0.91
    deepEqual
    -0.91
     reduce
    -0.90
    POSITIVE LOGITS
     Condiciones
    1.05
     Construcción
    1.04
     Lleva
    0.99
     alcune
    0.97
     será
    0.97
     Ubicación
    0.96
     Ofrece
    0.94
     Resolución
    0.94
     Conferencia
    0.94
     REALLY
    0.93
    Activations Density 0.022%

    No Known Activations