© 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. 34-GEMMASCOPE-RES-131K
    7. 84254
    Prev
    Next
    INDEX
    Explanations

    symbols preceding new phrases

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

    The neuron is activated by end‐of‐sentence punctuation (periods marking sentence boundaries).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     if
    -1.22
    他现在
    -1.10
    他已经
    -0.98
     '['
    -0.95
     there
    -0.94
    幸好
    -0.90
    何况
    -0.89
    更何况
    -0.88
     unserer
    -0.87
     eri
    -0.86
    POSITIVE LOGITS
    Unexpected
    1.22
    sequently
    1.11
     Unexpected
    1.05
    之后
    1.05
     coupled
    1.02
     facts
    0.93
    可能是
    0.93
    后的
    0.91
    功夫
    0.90
     subsequently
    0.90
    Activations Density 0.002%

    No Known Activations