© 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. 130167
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric tokens (numbers or digits) wherever they appear.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    named entities and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     proveedores
    -1.05
     exactement
    -1.00
     specif
    -0.97
     ridiculously
    -0.95
     ajouter
    -0.95
    っこ
    -0.94
    凩
    -0.93
     idiotic
    -0.92
     conferencias
    -0.92
     najleps
    -0.92
    POSITIVE LOGITS
     from
    1.08
     with
    1.08
     now
    0.94
     徒歩
    0.90
    ุ
    0.89
     while
    0.84
    ともに
    0.84
     hadapan
    0.83
     more
    0.83
     can
    0.82
    Activations Density 0.013%

    No Known Activations