© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71371
    Prev
    Next
    INDEX
    Explanations

    Comparison

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

    The neuron predominantly fires on numerical tokens (digits or numbers, including integers and decimals).

    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
    袈
    -0.90
     weißem
    -0.89
    必定
    -0.87
    이며
    -0.84
    splitting
    -0.83
     conception
    -0.83
    Conception
    -0.81
     solemnly
    -0.81
     afore
    -0.80
     SECON
    -0.79
    POSITIVE LOGITS
     вѣ
    1.02
    您可以
    0.90
    unku
    0.86
     Meningkatkan
    0.85
    áticas
    0.85
     править
    0.84
     ditemui
    0.84
    بلغ
    0.82
    fabs
    0.82
     Comparison
    0.81
    Activations Density 0.193%

    No Known Activations