© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45598
    Prev
    Next
    INDEX
    Explanations

    initials and abbreviations

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

    The neuron responds to isolated numeric tokens and uppercase abbreviations or acronyms (e.g. “DS,” “GP,” “H1B”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     there
    -1.79
    賡
    -1.75
    蕯
    -1.64
    </h4>
    -1.62
    鯔
    -1.49
    什么的
    -1.48
    犽
    -1.48
    結果は
    -1.48
    ytu
    -1.47
    却被
    -1.47
    POSITIVE LOGITS
    ’
    1.65
    ſſen
    1.48
    
    1.45
     focuses
    1.41
     ไม่
    1.40
     entrepreneur
    1.39
    MAXN
    1.38
     usando
    1.35
    ⏑
    1.28
    viii
    1.27
    Activations Density 0.006%

    No Known Activations