© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67063
    Prev
    Next
    INDEX
    Explanations

    price per unit

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

    This neuron activates on numeric tokens (numbers and digits) 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
    setTotal
    -0.89
    جاج
    -0.83
    värr
    -0.82
     Gerais
    -0.82
     INCOME
    -0.79
    istanbul
    -0.79
    dialog
    -0.75
    regexp
    -0.74
    Kü
    -0.73
    ｸ
    -0.73
    POSITIVE LOGITS
     each
    1.20
     per
    1.19
     لكل
    1.05
     каждого
    1.02
    每一
    1.01
    чень
    0.98
     לכל
    0.98
     każdej
    0.95
     هر
    0.95
     setiap
    0.94
    Activations Density 0.039%

    No Known Activations