© 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. 84359
    Prev
    Next
    INDEX
    Explanations

    [@ followed by number or capitalization

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

    The neuron primarily activates on numeric tokens or digit sequences.

    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
     déten
    -0.87
     nachfol
    -0.85
     投稿
    -0.85
    哗
    -0.82
    北海道
    -0.82
    żeli
    -0.82
    \"");
    -0.81
    {}",
    -0.81
    údos
    -0.79
    ueel
    -0.78
    POSITIVE LOGITS
     its
    1.03
    していて
    0.91
    でしたか
    0.90
     mirar
    0.88
     siente
    0.87
     will
    0.86
    municipi
    0.84
     therein
    0.82
     change
    0.82
     ohne
    0.81
    Activations Density 0.020%

    No Known Activations