© 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. 95758
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and symbols

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

    The neuron fires on that special Unicode whitespace character (the U+2004‐style space) whenever it appears.

    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
     before
    -1.15
    🤸
    -1.05
     berpeng
    -0.99
    ˂
    -0.98
     system
    -0.97
    ℅
    -0.96
     گوشی
    -0.96
    ❣️
    -0.94
    »),
    -0.94
     yzf
    -0.94
    POSITIVE LOGITS
     beschränkt
    1.16
     MAKES
    1.15
    uristic
    1.10
    有时候
    1.09
    大好きな
    1.05
    ebly
    1.05
    ὸν
    1.05
     PROVIDE
    1.05
     некоторых
    1.03
    licopter
    1.02
    Activations Density 0.000%

    No Known Activations