© 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. 35761
    Prev
    Next
    INDEX
    Explanations

    entities presented as both

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

    The neuron is keyed to colon punctuation (the “:”) that introduces explanations or lists.

    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
     even
    -0.92
    了许多
    -0.91
     réalisateur
    -0.90
    ereo
    -0.89
    gnügen
    -0.88
    流石
    -0.87
     varia
    -0.87
     compositeur
    -0.85
    esia
    -0.85
    เพิ่มเติม
    -0.84
    POSITIVE LOGITS
    Both
    1.34
     दोनों
    1.16
    Similarly
    1.11
     Both
    1.08
     similar
    1.05
     Similarly
    1.02
     Similar
    1.00
    Similar
    0.98
     similares
    0.96
     beide
    0.95
    Activations Density 0.071%

    No Known Activations