© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40275
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

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

    The neuron activates on numeric tokens (numbers or measurements) 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
     >
    -1.03
     unusually
    -1.00
     for
    -0.97
     all
    -0.97
     Because
    -0.94
     usually
    -0.94
     our
    -0.93
     which
    -0.93
     Unlike
    -0.93
     typically
    -0.92
    POSITIVE LOGITS
     faciliter
    1.12
     râ
    1.09
     bourg
    1.09
     publice
    1.05
     dentes
    1.01
    apest
    1.00
    composed
    0.98
    κη
    0.98
     ſever
    0.96
     wacky
    0.96
    Activations Density 0.044%

    No Known Activations