© 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. 33537
    Prev
    Next
    INDEX
    Explanations

    require(../, Insurgency, An independent, Edivoxetine

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

    The neuron strongly activates on numeric tokens (digits or multi‐digit numbers), such as timestamps, ranges, coordinates, and other numeric values.

    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
     tertentu
    -1.09
     from
    -1.08
     since
    -1.04
     enkelte
    -1.03
     někter
    -0.98
     againſt
    -0.98
    Sucesor
    -0.95
     kitabı
    -0.95
    Története
    -0.94
     saar
    -0.93
    POSITIVE LOGITS
     empresarios
    0.95
     reconocidos
    0.92
     descubierto
    0.88
    っちゃう
    0.85
    ʁ
    0.84
     ingenieros
    0.82
     ರ
    0.81
    斯克
    0.81
     ഗ
    0.80
     obreros
    0.79
    Activations Density 0.002%

    No Known Activations