© 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. 12782
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

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

    The neuron is picking out the neuter pronoun “it.”

    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
    EndInit
    -1.25
     Dizziness
    -1.13
     Aluno
    -1.11
    
    -1.11
     fofo
    -1.09
    Ⲉ
    -1.09
     suco
    -1.07
    えっ
    -1.06
     FINDINGS
    -1.06
     retrô
    -1.05
    POSITIVE LOGITS
    上面的
    1.10
    </strong>
    1.05
     χρόνια
    1.05
     it
    1.04
     urbanas
    1.03
    y
    1.03
    矢量
    1.01
    ль
    0.98
    它的
    0.98
    ti
    0.94
    Activations Density 0.088%

    No Known Activations