© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86433
    Prev
    Next
    INDEX
    Explanations

    New Jersey

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

    The neuron detects occurrences of the abbreviation “NJ” immediately followed by a numeric code (e.g. “NJ 350,” “NJ 316,” etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    0
    -2.95
    一種
    -2.84
    </h3>
    -2.63
    </strong>
    -2.42
    lossians
    -2.39
    ᥬ
    -2.39
    尛
    -2.34
    7
    -2.33
     всех
    -2.30
     durchgeführt
    -2.30
    POSITIVE LOGITS
    ра
    2.95
     was
    2.91
    ra
    2.70
     公园
    2.69
    逦
    2.56
     itſelf
    2.52
    ⢊
    2.45
    釹
    2.41
    🤍
    2.39
    ?"
    2.38
    Activations Density 0.003%

    No Known Activations